A high-performance computer vision system designed to detect the 67 gesture and trigger real-time multimedia responses. The system uses YOLO-Pose for motion tracking and provides live performance analytics.
- Real-time Gesture Detection: Uses advanced pose estimation to track wrist oscillation.
- Multimedia Integration: Automatically plays audio and displays image overlays upon successful detection.
- Performance Analytics: Tracks total detections and frequency (67s per minute).
- Optimized Pipeline: Non-blocking audio playback and efficient frame processing.
- Python 3.8+
- macOS (required for native audio playback via afplay)
-
Clone the repository:
git clone https://github.com/yourusername/SixtySevenDetector.git cd SixtySevenDetector -
Install dependencies:
pip install -r requirements.txt
-
Add your assets: Create an
assets/directory in the root and add the following files:assets/sound.mp3: The sound effect to play.assets/67_kid.jpg: The image to overlay.
Run the main detection script:
python3 main.pyPerform the 67 gesture (rapid up-and-down wrist movement) in front of the camera to trigger the system.
- Detection Sensitivity: Adjusted in
src/detector.pyviaMIN_MOVEMENT_PIXELS. - Audio Cooldown: Managed in
src/action.py(default: 10 seconds). - Image Duration: Managed in
main.py(default: 0.5 seconds).
The project is structured modularly:
main.py: Entry point and UI overlay logic.src/detector.py: Core gesture analysis.src/action.py: Multimedia trigger handling.src/vision.py: Camera stream management.
This project is licensed under the MIT License - see the LICENSE file for details.
Disclaimer: This project is for educational and entertainment purposes.