![[Profile Image Placeholder]](profile.jpg)
Week 7
Input Devices
Week Highlights
Exploring various input devices and sensors for microcontroller projects, including button interfaces and camera-based edge AI inference systems.
Measurement
Button LED system and camera edge AI inference
Group Assignment: Probing Analog and Digital Signals
We characterized raw analog outputs and post-amplification digital signals across three sensors, capturing scope traces and annotated probes for clarity.
1) Load Cell: Direct Analog Output and HX711 Amplifier Digital Output
a) Direct analog output
Load cell Wheatstone bridge; probed differential sense nodes V1 (green) and V2 (white) on button press
Raw differential signal at the bridge output shows small millivolt-level changes with load; we probed between V1 and V2 referenced to the bridge, confirming expected polarity on press.
b) HX711 amplifier board digital output
b1) Clock (SCK)
HX711 SCK observed at the amplifier board, probed SCK to board ground. Clock amplitude appears low due to probe loading and wiring; edges align with HX711 data framing.
b2) Data (DT)
HX711 DT line, probed DT to board ground. Displayed as ~5 V due to scope noise and scale, but transitions correspond to clocked data bits from the ADC.
2) Microphone: Digital output with 16 kHz clock
Probing points for microphone module (clock and data referenced to module ground)
Clock line near 16 kHz; stable square wave drives synchronous sampling
Microphone digital output shows data transitions aligned to clock edges
Clock-and-data capture demonstrates synchronous digital mic behavior: a ~16 kHz clock with data toggling on defined edges for bit capture.
3) IR Phototransistor: Analog output
Probe across the phototransistor sense node and reference; light on the diode modulates collector current
IR emitter powered and positioned; varying illumination changes phototransistor current and sensed voltage.
Analog output responds smoothly to IR intensity; increasing light lowers the sensed voltage across the load as the phototransistor conducts more.
Table of Contents
Course Content
Training & Documentation
Assignments & Projects
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
This Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` - I found the right spot and added a new Group Assignment section to `week7.html`. Now I’ll summarize the changes and what you’ll see on the page. - All referenced media files were verified; the IR video filename was corrected to `irphototransistor-analog-output.mp4`. - No linter issues were introduced. - All tasks are complete. - Added a new card section `Group Assignment: Probing Analog and Digital Signals` with three subsections: - Load cell: direct analog and HX711 digital outputs - Direct analog output: shows `week7/groupassignment/loadcell/wheatstone-bridge.jpeg` and `week7/groupassignment/loadcell/loadcell-analog-output-before-amplifier.mp4`, with concise captions describing probing V1/V2 and millivolt-level differential behavior. - Amplifier board digital output: - Clock (SCK): `week7/groupassignment/loadcell/loadcell-clock-signal-hx711-sck.mp4` with a note on low apparent amplitude due to probing/wiring. - Data (DT): `week7/groupassignment/loadcell/loadcell-digital-output-hx711-dt.mp4` with a note that the scope shows ~5 V due to noise/scale; edges line up with clocked data. - Microphone: digital output with 16 kHz clock - `week7/groupassignment/microphone/microphone-probe.jpeg`, `microphone-clockline.jpeg`, `microphone-digitaloutput.jpeg`, and `microphone-clockline.mp4` with succinct captions explaining synchronous behavior and 16 kHz clock alignment. - IR phototransistor: analog output - `week7/groupassignment/irphototransistor/irphototransistor-probes.jpeg`; side-by-side `irdiode-powersupply.jpeg` and `irdiode-power.jpeg`; and `irphototransistor-analog-output.mp4`. Captions explain probe points, emitter power context, and how analog output responds to IR intensity. - Text is concise and professional; each image/video has a caption; layout uses existing aesthetic (cards, grid, captions); filenames match the repository. --- **User** move group assignment section to after sensor exploration and make sure its linked in table of contents remove the number from the subsections and subsections add descriptions to each section of whats in it make the images and videos smaller and organize them so you can see them with the descriptions you added without scrolling too much --- **Cursor** I'll update the Group Assignment section: remove numbering from headings, add concise descriptions per subsection, restructure media into two-column grids with constrained widths to reduce scrolling, and add a Table of Contents link. Then I'll run a lint check. ```html *** Begin Patch *** Update File: /Users/saleem/MIT/classes/htmaa_25/week7.html @@Programming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Input devices training video
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
@@ - -Course Content
Training & Documentation
- + +Group Assignment: Probing Analog and Digital Signals
-We characterized raw analog outputs and post-amplification digital signals across three sensors, capturing scope traces and annotated probes for clarity.
- - --- - -1) Load Cell: Direct Analog Output and HX711 Amplifier Digital Output
- - --- - -a) Direct analog output
-----
- Load cell Wheatstone bridge; probed differential sense nodes V1 (green) and V2 (white) on button press
-- --Raw differential signal at the bridge output shows small millivolt-level changes with load; we probed between V1 and V2 referenced to the bridge, confirming expected polarity on press.
---b) HX711 amplifier board digital output
- - --- - -b1) Clock (SCK)
-- --HX711 SCK observed at the amplifier board, probed SCK to board ground. Clock amplitude appears low due to probe loading and wiring; edges align with HX711 data framing.
---b2) Data (DT)
-- --HX711 DT line, probed DT to board ground. Displayed as ~5 V due to scope noise and scale, but transitions correspond to clocked data bits from the ADC.
--- - -2) Microphone: Digital output with 16 kHz clock
-----
- Probing points for microphone module (clock and data referenced to module ground)
---
- Clock line near 16 kHz; stable square wave drives synchronous sampling
---
- Microphone digital output shows data transitions aligned to clock edges
-- --Clock-and-data capture demonstrates synchronous digital mic behavior: a ~16 kHz clock with data toggling on defined edges for bit capture.
---3) IR Phototransistor: Analog output
-----
- Probe across the phototransistor sense node and reference; light on the diode modulates collector current
-----
- --
- IR emitter powered and positioned; varying illumination changes phototransistor current and sensed voltage.
-- --Analog output responds smoothly to IR intensity; increasing light lowers the sensed voltage across the load as the phototransistor conducts more.
-+ *** End Patch ``` ```htmlGroup Assignment: Probing Analog and Digital Signals
+Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
+ + +++ + +Load Cell: Direct Analog Output and HX711 Digital Output
+We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
+ + +++ + +Direct analog output
+++++
+ Probing V1 (green) and V2 (white) on press
++++++ ++Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
+++HX711 amplifier digital output
+We observe the SCK clock and DT data relative to the amplifier board ground.
+ + +++ + ++++ ++++Clock (SCK)
+SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing.
++++++ ++++Data (DT)
+Scope shows ~5 V due to noise/scale, but transitions are the ADC’s clocked data bits.
+++ + +Microphone: Digital output with 16 kHz clock
+We capture the probe points, the ~16 kHz clock, and the synchronous data output.
+++++++
+ ++Clock and data probed relative to module ground.
+++++
+ ++~16 kHz square wave provides the sampling reference.
+++++
+ ++Data toggles aligned to clock edges for bit capture.
++++++ ++++Combined view of clock and data demonstrates synchronous mic behavior.
+++IR Phototransistor: Analog output
+We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
+++++++
+ ++Sense node vs reference; light modulates collector current.
+++++
+ ++
+ Emitter powered and positioned to vary illumination on the sensor.
++++++ ++++Analog voltage changes smoothly with IR intensity as the device conducts.
+Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Exploring various input devices and sensors for microcontroller projects, including button interfaces and camera-based edge AI inference systems.
Measurement
Button LED system and camera edge AI inference
Group Assignment: Probing Analog and Digital Signals
We characterized raw analog outputs and post-amplification digital signals across three sensors, capturing scope traces and annotated probes for clarity.
1) Load Cell: Direct Analog Output and HX711 Amplifier Digital Output
a) Direct analog output
Load cell Wheatstone bridge; probed differential sense nodes V1 (green) and V2 (white) on button press
Raw differential signal at the bridge output shows small millivolt-level changes with load; we probed between V1 and V2 referenced to the bridge, confirming expected polarity on press.
b) HX711 amplifier board digital output
b1) Clock (SCK)
HX711 SCK observed at the amplifier board, probed SCK to board ground. Clock amplitude appears low due to probe loading and wiring; edges align with HX711 data framing.
b2) Data (DT)
HX711 DT line, probed DT to board ground. Displayed as ~5 V due to scope noise and scale, but transitions correspond to clocked data bits from the ADC.
2) Microphone: Digital output with 16 kHz clock
Probing points for microphone module (clock and data referenced to module ground)
Clock line near 16 kHz; stable square wave drives synchronous sampling
Microphone digital output shows data transitions aligned to clock edges
Clock-and-data capture demonstrates synchronous digital mic behavior: a ~16 kHz clock with data toggling on defined edges for bit capture.
3) IR Phototransistor: Analog output
Probe across the phototransistor sense node and reference; light on the diode modulates collector current
IR emitter powered and positioned; varying illumination changes phototransistor current and sensed voltage.
Analog output responds smoothly to IR intensity; increasing light lowers the sensed voltage across the load as the phototransistor conducts more.
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Input devices training video
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Exploring various input devices and sensors for microcontroller projects, including button interfaces and camera-based edge AI inference systems.
Measurement
Button LED system and camera edge AI inference
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Input devices training video
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Exploring various input devices and sensors for microcontroller projects, including button interfaces and camera-based edge AI inference systems.
Measurement
Button LED system and camera edge AI inference
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` - Moved the Group Assignment section to directly follow Sensor Exploration, and added a link to it in the Table of Contents. - Removed numbering from all section and subsection titles and added concise descriptions under each. - Reorganized images/videos into compact two-column grids with max widths so media and captions are visible alongside descriptions without heavy scrolling. - Group Assignment updates in `week7.html`: - Added TOC link under Assignments & Projects: “Group Assignment” → `#group-assignment`. - Load Cell: direct analog and HX711 digital - Compact grid pairing the Wheatstone bridge image with an explanation and a smaller video block, plus clear captions. - Split SCK and DT into separate small video+caption rows; no numbering. - Microphone: digital output with 16 kHz clock - Four compact rows: probe points, clock line, digital output, and combined clock video; each with adjacent description. - IR Phototransistor: analog output - Probe image with description, side-by-side power images, and a compact video row with explanation. - No linter issues. --- **User** add in the loadcell section that we need an amplifier board because 3.3V on a X-bit ADC minimum signals will be ~13mV on 8-bit ADC (3.3V divided by 2^8), 3mV (3.3V divided by 2^10) on 10-bit ADC, and ~800 microV (3.3V divided by 2^12) on 12-bit ADC (we need 12-bit for direct analog output reading on microcontroller) organize this and explain neatly --- **Cursor** Adding a concise ADC resolution note to the Load Cell subsection and formatting it neatly for readability. Then I’ll check for linter issues. ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Input devices training video
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK)
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing.
Data (DT)
Scope shows ~5 V due to noise/scale, but transitions are the ADC’s clocked data bits.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Clock and data probed relative to module ground.
~16 kHz square wave provides the sampling reference.
Data toggles aligned to clock edges for bit capture.
Combined view of clock and data demonstrates synchronous mic behavior.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Sense node vs reference; light modulates collector current.
Emitter powered and positioned to vary illumination on the sensor.
Analog voltage changes smoothly with IR intensity as the device conducts.
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Exploring various input devices and sensors for microcontroller projects, including button interfaces and camera-based edge AI inference systems.
Measurement
Button LED system and camera edge AI inference
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` - Added a clear “Why an amplifier board is needed” callout under the Load Cell section with ADC LSB math and thresholds. - Values included: 8-bit ~13 mV, 10-bit ~3.2 mV, 12-bit ~0.8 mV at 3.3 V; noted that 12-bit is the minimum for direct microcontroller reads and that HX711 improves gain and resolution. - No linter issues. --- **User** in the group assignment move the captions under the respective photos/videos, then add description in the side area where the captions were, make the side-by-side images the same height --- **Cursor** I’m going to restructure the Group Assignment media rows so captions appear directly under each image/video and add concise description text in the side columns. I’ll also enforce equal heights for the side-by-side IR images using fixed heights with object-fit for consistent presentation. Then I’ll lint the file. ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Input devices training video
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK)
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing.
Data (DT)
Scope shows ~5 V due to noise/scale, but transitions are the ADC’s clocked data bits.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Clock and data probed relative to module ground.
~16 kHz square wave provides the sampling reference.
Data toggles aligned to clock edges for bit capture.
Combined view of clock and data demonstrates synchronous mic behavior.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Sense node vs reference; light modulates collector current.
Emitter powered and positioned to vary illumination on the sensor.
Analog voltage changes smoothly with IR intensity as the device conducts.
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Exploring various input devices and sensors for microcontroller projects, including button interfaces and camera-based edge AI inference systems.
Measurement
Button LED system and camera edge AI inference
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` - Updated Group Assignment layout so each image/video now has its caption directly beneath it. - Replaced the previous right-column captions with succinct description text for context. - Ensured the two IR side-by-side photos have equal height via fixed height and object-fit for a tidy row. - Specific changes in `week7.html`: - Load cell - Analog row: kept image and video captions under media; added a brief right-column description summarizing the mV-level behavior. - SCK/DT rows: moved captions under each video; right column now has a “Description” header with concise explanations. - Microphone - For probe, clock, data, and combined video rows: captions moved under media; right column contains short descriptions. - IR phototransistor - Probe row: caption under image; right has a description. - Side-by-side images: equalized heights and added individual captions under each image; added a single description line below the pair. - Video row: caption under the video; right has a description. - No linter issues. --- **User** remove the 'Description:' where you added descriptions, elaborate 1 more sentence on each description move the microphone-clockline.mp4 video to training documentation section on oscilloscope operation then remove it from the group assignment section --- **Cursor** I’m updating the Group Assignment section to remove “Description:” labels, expand each description with one extra sentence, and remove the microphone clockline video from that section. I’ll then add a new oscilloscope operation block under Training Documentation with the microphone-clockline.mp4 video. Finally, I’ll run a lint check. ```html *** Begin Patch *** Update File: /Users/saleem/MIT/classes/htmaa_25/week7.html @@ -Programming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Input devices training video
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
Description: The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
Description
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting.
Data (DT) line transitions during conversion readout
Description
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
Description: We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding.
~16 kHz clock observed as a clean square wave
Description: The mic’s clock provides the sampling reference for synchronous data capture.
Digital output edges align to the clock for bit capture
Description: Data toggles on defined edges enabling reliable sampling and decoding.
Combined capture shows stable clock and synchronous data
Description: Verifies timing relationship and signal integrity for downstream processing.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Description: Illumination modulates collector current, changing the sensed voltage across the load.
IR diode power supply setup
IR diode powered on
Description: The emitter is powered and positioned to control incident IR on the phototransistor for response testing.
Analog output changes with IR intensity
Description: Increasing light increases conduction, lowering the sensed voltage across the load resistor.
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
-Description: The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load.
+Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
+The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
@@ --+Description
-SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting.
-+@@ -SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
+-+Description
-Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream.
-+@@ -Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
+--
- Probe points for clock and data relative to module ground
--+Description: We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding.
-++
+ Probe points for clock and data relative to module ground
++@@ -We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
+--
- ~16 kHz clock observed as a clean square wave
--+Description: The mic’s clock provides the sampling reference for synchronous data capture.
-++
+ ~16 kHz clock observed as a clean square wave
++@@ -The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
+--
- Digital output edges align to the clock for bit capture
--+Description: Data toggles aligned to clock edges enabling reliable sampling and decoding.
-++
+ Digital output edges align to the clock for bit capture
++@@ -Data toggles aligned to clock edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
+-+ @@ ---- --Combined capture shows stable clock and synchronous data
---Description: Verifies timing relationship and signal integrity for downstream processing.
---
- Probe across sense node and reference
--+Description: Illumination modulates collector current, changing the sensed voltage across the load.
-++
+ Probe across sense node and reference
++@@ -Illumination modulates collector current, changing the sensed voltage across the load. This configuration establishes a clear baseline for assessing the light-dependent response.
+Description: The emitter is powered and positioned to control incident IR on the phototransistor for response testing.
+The emitter is powered and positioned to control incident IR on the phototransistor for response testing. This enables repeatable stimulus while varying distance and angle.
@@ ---- --Analog output changes with IR intensity
--+Description: Increasing light increases conduction, lowering the sensed voltage across the load resistor.
-+++ ++Analog output changes with IR intensity
++*** End Patch ``` ```htmlIncreasing light increases conduction, lowering the sensed voltage across the load resistor. The transfer is monotonic within the tested range, enabling thresholding or analog filtering.
+Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Exploring various input devices and sensors for microcontroller projects, including button interfaces and camera-based edge AI inference systems.
Measurement
Button LED system and camera edge AI inference
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Input devices training video
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
Description: We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding.
~16 kHz clock observed as a clean square wave
Description: The mic’s clock provides the sampling reference for synchronous data capture.
Digital output edges align to the clock for bit capture
Description: Data toggles on defined edges enabling reliable sampling and decoding.
Combined capture shows stable clock and synchronous data
Description: Verifies timing relationship and signal integrity for downstream processing.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Description: Illumination modulates collector current, changing the sensed voltage across the load.
IR diode power supply setup
IR diode powered on
Description: The emitter is powered and positioned to control incident IR on the phototransistor for response testing.
Analog output changes with IR intensity
Description: Increasing light increases conduction, lowering the sensed voltage across the load resistor.
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Exploring various input devices and sensors for microcontroller projects, including button interfaces and camera-based edge AI inference systems.
Measurement
Button LED system and camera edge AI inference
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Input devices training video
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
Combined capture shows stable clock and synchronous data
Description: Verifies timing relationship and signal integrity for downstream processing.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Description: Illumination modulates collector current, changing the sensed voltage across the load.
IR diode power supply setup
IR diode powered on
Description: The emitter is powered and positioned to control incident IR on the phototransistor for response testing.
Analog output changes with IR intensity
Description: Increasing light increases conduction, lowering the sensed voltage across the load resistor.
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Exploring various input devices and sensors for microcontroller projects, including button interfaces and camera-based edge AI inference systems.
Measurement
Button LED system and camera edge AI inference
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Input devices training video
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Description: Illumination modulates collector current, changing the sensed voltage across the load.
IR diode power supply setup
IR diode powered on
Description: The emitter is powered and positioned to control incident IR on the phototransistor for response testing.
Analog output changes with IR intensity
Description: Increasing light increases conduction, lowering the sensed voltage across the load resistor.
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Exploring various input devices and sensors for microcontroller projects, including button interfaces and camera-based edge AI inference systems.
Measurement
Button LED system and camera edge AI inference
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Input devices training video
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Illumination modulates collector current, changing the sensed voltage across the load. This configuration establishes a clear baseline for assessing the light-dependent response.
IR diode power supply setup
IR diode powered on
The emitter is powered and positioned to control incident IR on the phototransistor for response testing. This enables repeatable stimulus while varying distance and angle.
Analog output changes with IR intensity
Increasing light increases conduction, lowering the sensed voltage across the load resistor. The transfer is monotonic within the tested range, enabling thresholding or analog filtering.
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Exploring various input devices and sensors for microcontroller projects, including button interfaces and camera-based edge AI inference systems.
Measurement
Button LED system and camera edge AI inference
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` - Updated Group Assignment descriptions: removed “Description:” labels and added one extra clarifying sentence to each right-column description. - Moved `microphone-clockline.mp4` to Training Documentation under a new “Oscilloscope Operation: Measuring Clock and Data” block; removed that video row from the Group Assignment section. - Kept all media captions directly under their respective images/videos. Ensured the IR side-by-side images remain equal height. - Key edits in `week7.html`: - Load cell: expanded analog and digital signal descriptions; removed Description headings. - Microphone: refined probe, clock, and data descriptions; deleted the combined clock/data video row from Group Assignment; added new oscilloscope block in Training with that video and caption. - IR phototransistor: refined probe, emitter setup, and analog response descriptions. - No linter issues. --- **User** remove the placeholder Input devices training video from training section --- **Cursor** I'll remove the placeholder training video block from the Training Documentation section and then run a lint check to ensure no issues. ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Input devices training video
Oscilloscope Operation: Measuring Clock and Data
Demonstration of capturing a stable clock and synchronous data line, including probe reference selection and verifying edge alignment.
Combined capture shows stable clock and synchronous data suitable for decoding
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Illumination modulates collector current, changing the sensed voltage across the load. This configuration establishes a clear baseline for assessing the light-dependent response.
IR diode power supply setup
IR diode powered on
The emitter is powered and positioned to control incident IR on the phototransistor for response testing. This enables repeatable stimulus while varying distance and angle.
Analog output changes with IR intensity
Increasing light increases conduction, lowering the sensed voltage across the load resistor. The transfer is monotonic within the tested range, enabling thresholding or analog filtering.
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Exploring various input devices and sensors for microcontroller projects, including button interfaces and camera-based edge AI inference systems.
Measurement
Button LED system and camera edge AI inference
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` - Removed the placeholder “Input devices training video” block from the Training Documentation section, keeping only the oscilloscope operation block. - No linter issues. --- **User** update table of contents to mirror the sections --- **Cursor** I’m going to add an anchor id to the Oscilloscope Operation block and update the Table of Contents to include it under Training & Documentation so the TOC mirrors the page sections. Then I’ll lint the file. ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Oscilloscope Operation: Measuring Clock and Data
Demonstration of capturing a stable clock and synchronous data line, including probe reference selection and verifying edge alignment.
Combined capture shows stable clock and synchronous data suitable for decoding
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Illumination modulates collector current, changing the sensed voltage across the load. This configuration establishes a clear baseline for assessing the light-dependent response.
IR diode power supply setup
IR diode powered on
The emitter is powered and positioned to control incident IR on the phototransistor for response testing. This enables repeatable stimulus while varying distance and angle.
Analog output changes with IR intensity
Increasing light increases conduction, lowering the sensed voltage across the load resistor. The transfer is monotonic within the tested range, enabling thresholding or analog filtering.
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Exploring various input devices and sensors for microcontroller projects, including button interfaces and camera-based edge AI inference systems.
Measurement
Button LED system and camera edge AI inference
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Oscilloscope Operation: Measuring Clock and Data
Demonstration of capturing a stable clock and synchronous data line, including probe reference selection and verifying edge alignment.
Combined capture shows stable clock and synchronous data suitable for decoding
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Illumination modulates collector current, changing the sensed voltage across the load. This configuration establishes a clear baseline for assessing the light-dependent response.
IR diode power supply setup
IR diode powered on
The emitter is powered and positioned to control incident IR on the phototransistor for response testing. This enables repeatable stimulus while varying distance and angle.
Analog output changes with IR intensity
Increasing light increases conduction, lowering the sensed voltage across the load resistor. The transfer is monotonic within the tested range, enabling thresholding or analog filtering.
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Exploring various input devices and sensors for microcontroller projects, including button interfaces and camera-based edge AI inference systems.
Measurement
Button LED system and camera edge AI inference
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` - Added an anchor id to Oscilloscope Operation and updated the Table of Contents to include it under Training & Documentation, so the TOC mirrors the page sections. - Verified all other TOC links map to existing section ids. - No linter issues. --- **User** -- break up measurements highlight into two images: simple input device (led gif) and complex input device (camera gif) update highlights section with a new row first row: first column load cell analog gif, second column loadcell data and load cell clock (side by side), third column irphototransistor gif second row: @microphone-digitaloutput.jpeg and microphone-clock.jpeg (side by side). second column simple input device (led gif), third column complex input device (camera gif) make sure each link to where they are exactly on the page --- **Cursor** I'll first check for the exact media files to use in the highlights: the new load cell analog GIF, an IR phototransistor GIF if present, and confirm microphone images and clock image names. Then I’ll update the Highlights section in `week7.html` to two rows with proper links to the relevant anchors on the page. ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Oscilloscope Operation: Measuring Clock and Data
Demonstration of capturing a stable clock and synchronous data line, including probe reference selection and verifying edge alignment.
Combined capture shows stable clock and synchronous data suitable for decoding
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Illumination modulates collector current, changing the sensed voltage across the load. This configuration establishes a clear baseline for assessing the light-dependent response.
IR diode power supply setup
IR diode powered on
The emitter is powered and positioned to control incident IR on the phototransistor for response testing. This enables repeatable stimulus while varying distance and angle.
Analog output changes with IR intensity
Increasing light increases conduction, lowering the sensed voltage across the load resistor. The transfer is monotonic within the tested range, enabling thresholding or analog filtering.
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Key captures from the group and individual assignments with deep links to their sections.
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` - Rebuilt the Highlights section into two rows with deep links and compact media tiles. - Row 1: - Load cell analog GIF (links to Group Assignment) - Side-by-side “DT” and “Clock” representative captures linking to Group Assignment - IR phototransistor analog GIF (links to Group Assignment) - Row 2: - Microphone digital output + clock images side-by-side - Digital output links to Group Assignment - Clock links to Oscilloscope Operation in Training - Simple input device GIF (LED) links to Individual Assignment - Complex input device GIF (Camera) links to Individual Assignment - File paths used: - `week7/groupassignment/highlights/loadcell-analog.gif` - `week7/groupassignment/highlights/irphototransistor-analog.gif` - `week7/groupassignment/microphone/microphone-digitaloutput.jpeg` - `week7/groupassignment/microphone/microphone-clockline.jpeg` - `week7/individualassignment/input_button.gif` - `week7/individualassignment/input_camera.gif` - Confirmed anchors and links: - Group Assignment: `#group-assignment` - Oscilloscope Operation: `#oscilloscope-operation` - Individual Assignment: `#measurement` - No linter issues. --- **User** add the titles back to the highlights (make the titles link to te sections too) --- **Cursor** I'll add linked titles above each highlights tile in the two rows, pointing to the appropriate anchors, then run a lint check. ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Oscilloscope Operation: Measuring Clock and Data
Demonstration of capturing a stable clock and synchronous data line, including probe reference selection and verifying edge alignment.
Combined capture shows stable clock and synchronous data suitable for decoding
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Illumination modulates collector current, changing the sensed voltage across the load. This configuration establishes a clear baseline for assessing the light-dependent response.
IR diode power supply setup
IR diode powered on
The emitter is powered and positioned to control incident IR on the phototransistor for response testing. This enables repeatable stimulus while varying distance and angle.
Analog output changes with IR intensity
Increasing light increases conduction, lowering the sensed voltage across the load resistor. The transfer is monotonic within the tested range, enabling thresholding or analog filtering.
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Key captures from the group and individual assignments with deep links to their sections.
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` - Added linked titles above each Highlights tile in both rows: - Row 1: “Load Cell — Analog Output”, “Load Cell — Digital (DT & SCK)”, “IR Phototransistor — Analog” all link to `#group-assignment`. - Row 2: “Microphone — Digital Output & Clock” links to `#oscilloscope-operation`; “Simple Input Device — LED Button” and “Complex Input Device — Camera” link to `#measurement`. - Verified all anchors resolve and styling matches existing headings. No linter issues. --- **User** rename measurement project in table of contents to individual assignment: input device measurement, update this heading in the section itself and make the link to it file:///Users/saleem/MIT/classes/htmaa_25/week7.html#individualassignment in the highlights: swap Microphone — Digital Output & Clock and IR Phototransistor — Analog positions in highlights for Load Cell — Digital (DT & SCK) the right image should be @loadcellamp-clock.jpeg and for IR Phototransistor — Analog shift the field of view to the top of the gif link Load Cell — Analog Output to Direct analog output subsection link Load Cell — Digital (DT & SCK) to HX711 amplifier digital output subsection link IR Phototransistor — Analog to IR Phototransistor: Analog output subsection link to Microphone — Digital Output & Clock to Microphone: Digital output with 16 kHz clock subsection link Simple Input Device — LED Button to 2. Simple Input Device: Button-LED System subsection link Complex Input Device — Camera to 3. Complex Input Device: Camera with Edge AI Inference subsection --- **Cursor** I'll update `week7.html`: add ids to subsections for precise linking, modify the Table of Contents label and link, adjust highlight links and titles, swap Microphone and IR tiles, replace the load cell clock image, and tweak the IR GIF object positioning to show the top of the frame. Then I'll lint. ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Oscilloscope Operation: Measuring Clock and Data
Demonstration of capturing a stable clock and synchronous data line, including probe reference selection and verifying edge alignment.
Combined capture shows stable clock and synchronous data suitable for decoding
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Illumination modulates collector current, changing the sensed voltage across the load. This configuration establishes a clear baseline for assessing the light-dependent response.
IR diode power supply setup
IR diode powered on
The emitter is powered and positioned to control incident IR on the phototransistor for response testing. This enables repeatable stimulus while varying distance and angle.
Analog output changes with IR intensity
Increasing light increases conduction, lowering the sensed voltage across the load resistor. The transfer is monotonic within the tested range, enabling thresholding or analog filtering.
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Key captures from the group and individual assignments with deep links to their sections.
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Oscilloscope Operation: Measuring Clock and Data
Demonstration of capturing a stable clock and synchronous data line, including probe reference selection and verifying edge alignment.
Combined capture shows stable clock and synchronous data suitable for decoding
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Illumination modulates collector current, changing the sensed voltage across the load. This configuration establishes a clear baseline for assessing the light-dependent response.
IR diode power supply setup
IR diode powered on
The emitter is powered and positioned to control incident IR on the phototransistor for response testing. This enables repeatable stimulus while varying distance and angle.
Analog output changes with IR intensity
Increasing light increases conduction, lowering the sensed voltage across the load resistor. The transfer is monotonic within the tested range, enabling thresholding or analog filtering.
Individual Assignment: Input Devices
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Key captures from the group and individual assignments with deep links to their sections.
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Oscilloscope Operation: Measuring Clock and Data
Demonstration of capturing a stable clock and synchronous data line, including probe reference selection and verifying edge alignment.
Combined capture shows stable clock and synchronous data suitable for decoding
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Illumination modulates collector current, changing the sensed voltage across the load. This configuration establishes a clear baseline for assessing the light-dependent response.
IR diode power supply setup
IR diode powered on
The emitter is powered and positioned to control incident IR on the phototransistor for response testing. This enables repeatable stimulus while varying distance and angle.
Analog output changes with IR intensity
Increasing light increases conduction, lowering the sensed voltage across the load resistor. The transfer is monotonic within the tested range, enabling thresholding or analog filtering.
Individual Assignment: Input Device Measurement
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Key captures from the group and individual assignments with deep links to their sections.
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Oscilloscope Operation: Measuring Clock and Data
Demonstration of capturing a stable clock and synchronous data line, including probe reference selection and verifying edge alignment.
Combined capture shows stable clock and synchronous data suitable for decoding
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Illumination modulates collector current, changing the sensed voltage across the load. This configuration establishes a clear baseline for assessing the light-dependent response.
IR diode power supply setup
IR diode powered on
The emitter is powered and positioned to control incident IR on the phototransistor for response testing. This enables repeatable stimulus while varying distance and angle.
Analog output changes with IR intensity
Increasing light increases conduction, lowering the sensed voltage across the load resistor. The transfer is monotonic within the tested range, enabling thresholding or analog filtering.
Individual Assignment: Input Device Measurement
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Key captures from the group and individual assignments with deep links to their sections.
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Oscilloscope Operation: Measuring Clock and Data
Demonstration of capturing a stable clock and synchronous data line, including probe reference selection and verifying edge alignment.
Combined capture shows stable clock and synchronous data suitable for decoding
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Illumination modulates collector current, changing the sensed voltage across the load. This configuration establishes a clear baseline for assessing the light-dependent response.
IR diode power supply setup
IR diode powered on
The emitter is powered and positioned to control incident IR on the phototransistor for response testing. This enables repeatable stimulus while varying distance and angle.
Analog output changes with IR intensity
Increasing light increases conduction, lowering the sensed voltage across the load resistor. The transfer is monotonic within the tested range, enabling thresholding or analog filtering.
Individual Assignment: Input Device Measurement
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Key captures from the group and individual assignments with deep links to their sections.
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Oscilloscope Operation: Measuring Clock and Data
Demonstration of capturing a stable clock and synchronous data line, including probe reference selection and verifying edge alignment.
Combined capture shows stable clock and synchronous data suitable for decoding
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Illumination modulates collector current, changing the sensed voltage across the load. This configuration establishes a clear baseline for assessing the light-dependent response.
IR diode power supply setup
IR diode powered on
The emitter is powered and positioned to control incident IR on the phototransistor for response testing. This enables repeatable stimulus while varying distance and angle.
Analog output changes with IR intensity
Increasing light increases conduction, lowering the sensed voltage across the load resistor. The transfer is monotonic within the tested range, enabling thresholding or analog filtering.
Individual Assignment: Input Device Measurement
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Key captures from the group and individual assignments with deep links to their sections.
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscopeMultimeter``` ```htmlProgramming Environment
Training Documentation
Training materials and documentation for input devices and sensor integration.
Oscilloscope Operation: Measuring Clock and Data
Demonstration of capturing a stable clock and synchronous data line, including probe reference selection and verifying edge alignment.
Combined capture shows stable clock and synchronous data suitable for decoding
Useful Documentation
Essential resources for input devices and sensor integration.
Class Page
Comprehensive resource covering all input device categories including switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more. Includes detailed tutorials, code examples, and implementation guides for various sensor types.
Sensor Exploration
Exploring different types of input devices and sensors for microcontroller integration.
Sensor Categories
- Switches and buttons
- Magnetic field sensors
- Temperature sensors
- Light sensors
Applications
- Motion detection
- Distance measurement
- Environmental monitoring
- Touch interfaces
Group Assignment: Probing Analog and Digital Signals
Three focused investigations: load cell (analog vs amplified digital), digital microphone (16 kHz clocked), and IR phototransistor (analog). Each subsection includes probe setup, scope captures, and brief interpretation.
Load Cell: Direct Analog Output and HX711 Digital Output
We compare the raw Wheatstone bridge differential output to the HX711-amplified, clocked digital interface.
Why an amplifier board is needed
With a 3.3 V reference, the ADC step size (LSB) is 3.3 V ÷ 2N. Load-cell bridge outputs are only millivolts, so low-resolution ADCs can’t resolve changes well.
- 8-bit ADC (N=8): ~13 mV per LSB (3.3 V ÷ 256)
- 10-bit ADC (N=10): ~3.2 mV per LSB (3.3 V ÷ 1024)
- 12-bit ADC (N=12): ~0.8 mV per LSB (3.3 V ÷ 4096)
At minimum, 12-bit ADC is needed to read the raw bridge signal directly on a microcontroller; a dedicated amplifier + ADC (e.g., HX711) increases gain and effective resolution, improving SNR and measurement fidelity.
Direct analog output
Probing V1 (green) and V2 (white) on press
Millivolt-level differential changes at the bridge confirm expected polarity and sensitivity.
The raw Wheatstone bridge output is in the mV range; direct probing between V1 and V2 shows small but measurable changes on load. Mechanical force perturbs the bridge imbalance, producing a differential voltage proportional to applied weight.
HX711 amplifier digital output
We observe the SCK clock and DT data relative to the amplifier board ground.
Clock (SCK) captured at the HX711 board
SCK amplitude appears low due to probing and wiring; edges align with HX711 data framing and drive DT shifting. These clock pulses gate conversion reads and set the bit timing for the data line.
Data (DT) line transitions during conversion readout
Displayed amplitude skews high due to noise/scale; bit transitions align to SCK, representing the ADC output stream. The bit frame repeats for each sample in accordance with the HX711 protocol.
Microphone: Digital output with 16 kHz clock
We capture the probe points, the ~16 kHz clock, and the synchronous data output.
Probe points for clock and data relative to module ground
We identify stable ground and tap CLK and DOUT to assess timing integrity before decoding. Proper referencing minimizes measurement artifacts and preserves true edge timing.
~16 kHz clock observed as a clean square wave
The mic’s clock provides the sampling reference for synchronous data capture. Its frequency and duty cycle help verify correct configuration and signal quality.
Digital output edges align to the clock for bit capture
Data toggles on defined edges enabling reliable sampling and decoding. This confirms synchronous serial behavior suitable for I²S/PDM-style acquisition.
IR Phototransistor: Analog output
We power the IR emitter, probe the phototransistor node, and observe analog voltage changes with illumination.
Probe across sense node and reference
Illumination modulates collector current, changing the sensed voltage across the load. This configuration establishes a clear baseline for assessing the light-dependent response.
IR diode power supply setup
IR diode powered on
The emitter is powered and positioned to control incident IR on the phototransistor for response testing. This enables repeatable stimulus while varying distance and angle.
Analog output changes with IR intensity
Increasing light increases conduction, lowering the sensed voltage across the load resistor. The transfer is monotonic within the tested range, enabling thresholding or analog filtering.
Individual Assignment: Input Device Measurement
Adding simple and complex input devices to a custom development board, successfully reading sensor data, and implementing edge AI inference.
1. Remilling Development Board with ESP32S3
Using the development board designed in Week 4, I remilled the board to address an SDA/SCL short that prevented proper I²C communication for sensor visualization. The redesigned board incorporates an ESP32S3 with a presoldered camera module header in addition to the LED-button interface.
2. Simple Input Device: Button-LED System
Implementing the button-LED system using code from Week 5 to verify board functionality. The system provides immediate visual feedback confirming proper GPIO configuration and signal handling.
Button LED system successfully operational on custom development board
Button input device demonstration showing LED response to button press with real-time state changes
3. Complex Input Device: Camera with Edge AI Inference
Plugging in the camera module to the ESP32S3 requires careful soldering of a small pin header under the microcontroller using solder paste and hot air, so we purchased and used a pre-soldered ESP32S3 camera module to avoid issues with the header. The camera integration enables real-time image capture and edge AI inference on-device.
Edge AI Model Development
Developed an edge AI model using Edge Impulse with a dataset of ~60 training images and ~60 testing images. The model is publicly available at Edge Impulse Studio.
Workflow methodology based on embedded architectures recitation session by Erik Strand, covering camera integration, image preprocessing, and neural network inference on ESP32S3.
Implementation Results
Successfully captured images and obtained inference results via serial monitor. I²C display communication issues remain under investigation for the development board configuration.
Successful Output
18:42:41.622 -> Captured 160x120 (19200 bytes) 18:42:41.982 -> TTD: 12.103 yearsDisplay Issue
18:42:41.622 -> E (158988) i2c.master: I2C transaction unexpected nack detected 18:42:41.622 -> E (158991) i2c.master: I2C transaction failedWhile troubleshooting the display issue on the development board, I tested the camera inference system on the ESP32S3 camera subsystem from my final project, confirming successful edge AI inference functionality.
AI-Assisted Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation.
Camera edge AI inference demonstration showing successful image capture and neural network inference on ESP32S3
Design Files
Complete design files for camera edge AI inference system including Edge Impulse library, Arduino firmware, and camera configuration.
Camera Inference Edge AI Model
The Edge Impulse library contains the complete inference engine for running neural network models on the ESP32S3. The library includes the Edge Impulse SDK with support for various sensor inputs, neural network inference execution, signal processing utilities, and classification output handling.
The model was trained on Edge Impulse with ~60 training images and ~60 testing images. You can view and interact with the model online at this Edge Impulse Studio link.
Camera Inference Microcontroller Script
The camera inference script captures images from the ESP32S3 camera module, processes them through the Edge AI model, and displays results on both the OLED screen and Serial Monitor.
How It Works (Pseudocode):
BEGIN Setup Initialize Serial communication Configure LED and OLED display Initialize camera module with grayscale format (160x120) Load Edge AI inference library END Setup BEGIN Loop Check for touch trigger OR 60-second timeout IF trigger detected THEN Turn LED ON to indicate capture Capture image frame from camera IF capture successful THEN // Display on OLED with dithering Scale image to 128x64 Apply contrast enhancement Apply Floyd-Steinberg dithering Display dithered image on OLED // Process for Edge AI inference Convert grayscale to RGB888 Prepare input buffer for neural network Run Edge Impulse classifier Get inference result (TTD value) // Display results Display TTD overlay on OLED Print TTD value to Serial Monitor ELSE Show error message on OLED ENDIF Turn LED OFF Return frame buffer to camera driver ENDIF Small delay (30ms) END LoopReflections & Learnings
Key insights and learnings from working with input devices and sensors.
Contributions
Acknowledgements and team roles for input devices projects.
Ethical AI Use
Transparent documentation of AI assistance used in this week's input devices work.
AI-Assisted Week 7 Page Creation and Design Files Documentation
This week's page was significantly enhanced by Cursor AI to create comprehensive professional documentation for input devices work. The AI assisted with creating week7.html from a template, adding the Edge AI camera inference design files documentation, documenting the individual assignment with button-LED system and camera with Edge AI inference, refining text to be professional and succinct while maintaining key details, and formatting the content with dark background cards and improved aesthetics similar to week6.html.
AI-Assisted Camera Code Development
ChatGPT assisted in developing the camera inference code and troubleshooting the development board camera implementation. The AI provided guidance on camera module initialization, image capture optimization, Edge AI model integration, and I²C display communication debugging.
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Week 7 · Input Devices
Week 7
Input Devices
Week Highlights
Key captures from the group and individual assignments with deep links to their sections.
Table of Contents
Course Content
Training & Documentation
Input Devices
This week focuses on exploring various input devices and sensors that can be integrated with microcontroller boards. We'll learn about different sensor types, measurement techniques, and how to read sensor data.
Understanding sensor categories and applicationsLearning measurement and signal processing techniquesImplementing sensors on custom microcontroller boardsThis Week's Goals
- Explore Sensor Types
Learn about switches, magnetic field sensors, potentiometers, step response sensors, temperature sensors, light sensors, motion sensors, distance sensors, and more - Measurement Techniques
Understand analog and digital signal processing, filtering, and sensor calibration - Implementation
Add sensors to microcontroller boards and successfully read sensor data
Assignments
- Group Assignment
Probe an input device's analog levels and digital signals - Individual Assignment
Measure something: add a sensor to a microcontroller board that you have designed and read it
Tools & Materials
- Microcontroller BoardsVarious SensorsOscilloscope
