ESP32 CAM Object Detection using Edge Impulse TinyML

AI project uses Edge Impulse platform to train custom image classification model and deploy on ESP32-CAM for real-time object detection at the edge. Model identifies 3 classes: tomato, potato, onion (customizable). Data collection: use ESP32-CAM itself or smartphone via Edge Impulse QR code. Training: MobileNetV2 transfer learning on Edge Impulse cloud (free account). Deployment: Arduino library exported from Edge Impulse, imported into Arduino IDE and flashed to ESP32-CAM. Model runs inference on each captured frame and displays detected class and confidence on Serial Monitor and optional OLED screen. Inference time: 200-500ms per frame on ESP32 at 240MHz. Accuracy: 70-90% with 50+ images per class. Model size: ~200KB for MobileNet96 int8 quantized. Image input: 96x96 grayscale. Steps: 1) Create Edge Impulse project 2) Collect 50+ images per class 3) Train model 4) Export Arduino library 5) Include in sketch 6) Flash ESP32-CAM.

Detailed Project Description

ESP32 CAM Object Detection using Edge Impulse TinyML applies computer vision to camera frames to detect or recognise what is in view and act on the result automatically.

How It Works
1. The camera captures frames continuously.
2. Frames are pre-processed and fed to the detection/recognition model.
3. Detections are drawn on the output and used to trigger the required action (log, alert, unlock, count).
4. Results and images are stored or streamed to a browser/dashboard.

Key Components and Their Role
- ESP32-CAM: ESP32 module with an OV2640 camera used to capture images or stream video.
- Arduino: microcontroller board that reads the inputs, runs the control logic and drives the outputs.
- OLED display (SSD1306): 128x64 I2C display used to show live readings and status.
- Camera module: image sensor used for capture, streaming or computer vision.
- Edge Impulse: TinyML platform used to train and deploy the on-device model.

Implementation Steps
1. Collect the components and study each module's datasheet (pin-out, voltage, interface).
2. Wire the circuit on a breadboard following the pin mapping; power sensors from the correct rail (3.3 V / 5 V).
3. Install Arduino IDE, Edge Impulse Studio, Edge Impulse Arduino Library and the required libraries; flash a minimal test sketch for each module separately.
4. Write the main firmware: read sensors → process → drive outputs / send data.
5. Configure network or cloud credentials and test communication end-to-end.
6. Calibrate thresholds, add error handling (reconnect, sensor time-out) and run a long-duration test.
7. Finalise on a PCB / enclosure and document wiring, code and results.

Key Features
- Real-time detection
- Annotated output
- Event logging
- Adjustable confidence threshold

Expected Output
On completion the student will have a live video/image feed with detected objects highlighted and the corresponding actions logged.

Deliverables
- Complete source code with comments
- Circuit diagram and pin mapping
- Project report with screenshots and results
- Demonstration-ready build