🥊 PunchTracker - AI Boxing Assistant 🥊

A real-time boxing assistant application that uses computer vision and machine learning to track, count, and analyze your punches.

✨ Features

• 📹 Real-time webcam punch detection
• 🔍 Advanced pose estimation using TensorFlow's MoveNet
• 👊 Detects and classifies different punch types (jabs, crosses, hooks, uppercuts)
• 📊 Live statistics and performance tracking
• 🎯 Visual feedback for punch detection
• 🔧 User calibration for personalized detection
• 💾 Session history and progress tracking
• 📈 Performance analytics and visualization

🚀 Tech Stack

• Machine Learning: TensorFlow + TensorFlow Hub
• Computer Vision: OpenCV
• Data Processing: NumPy
• Visualization: Matplotlib
• Data Storage: SQLite

🛠️ Installation

Prerequisites

• Python 3.8 or higher
• Webcam
• Required libraries (see requirements.txt)

Setup

1. Clone the repository:

   git clone https://github.com/yourusername/punchtracker.git
   cd punchtracker

2. Create a virtual environment (optional but recommended):

   python -m venv venv

3. Activate the virtual environment:

   • Windows:

     venv\Scripts\activate

   • macOS/Linux:

     source venv/bin/activate

4. Install the required dependencies:

   pip install -r requirements.txt

📋 Usage

1. Start the application:

   python main.py

2. Controls:

   • ESC: Exit the application
   • C: Start calibration
   • D: Toggle debug view (shows skeleton)
   • R: Reset current session
   • S: Show detailed statistics

3. Calibration:

   • Follow the on-screen instructions to calibrate the application to your movements
   • Move through each step of different punch types
   • The system will adjust its detection parameters to your specific style

📊 Data Storage

All session data is stored in a local SQLite database in the data folder. This includes:

• Session date and duration
• Total punch count and types
• Punches per minute
• Historical performance data

🏗️ Project Structure

punchtracker/
├── main.py              # Main application entry point
├── requirements.txt     # Required dependencies
├── data/                # Session data storage
├── models/              # Model storage (downloaded automatically)
└── utils/
    ├── pose_detector.py # TensorFlow pose detection module
    ├── punch_counter.py # Punch detection and classification
    ├── ui_manager.py    # UI and visualization components
    ├── data_manager.py  # Data storage and retrieval
    └── calibration.py   # User calibration system

🔧 Advanced Configuration

The application can be customized by modifying the following parameters:

• Pose Detection: Change model type in pose_detector.py (lightning or thunder)
• Detection Sensitivity: Adjust thresholds in punch_counter.py
• UI Customization: Modify colors and layout in ui_manager.py

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgements

• TensorFlow for the MoveNet model
• OpenCV for computer vision capabilities
• NumPy and Matplotlib for data processing and visualization

🌟 Future Features / Contributing Ideas

Looking for ways to contribute or curious about what's next? Check out our list of feature ideas!

---

Made with ❤️ by Anthony M