✋ Pong Game with Hand Gesture Control

This is an AI-powered Pong game that uses real-time hand gesture recognition to control paddles using your webcam. Open hands detected on either side of the screen move the paddles up or down — no keyboard or mouse needed!

Demo

---

🎮 Features

• Real-time hand detection with TensorFlow and pre-trained model
• Gesture-based paddle movement (open hand = move)
• Split-screen detection for two-player interaction
• Pong gameplay with paddle & ball physics in Pygame
• Overlays interactive regions and visual cues using OpenCV

---

🧠 Technologies Used

• TensorFlow for hand detection
• OpenCV for camera feed and visualization
• Pygame for game mechanics
• NumPy for image and numerical operations

---

🛠️ Installation

1. Clone this repository

git clone https://github.com/yourusername/pong-motion-control.git
cd pong-motion-control

2. Install dependencies

pip install pygame opencv-python tensorflow numpy

3. Add your pre-trained TensorFlow model to src/pretrained_model.pb

---

▶️ Run the Game

python main.py

Press SPACE to start the game Press ESC to exit

---

🎯 Controls

• Open your hand in the top area → Move paddle up
• Open your hand in the bottom area → Move paddle down

Left hand = Player 1 Right hand = Player 2

---

📂 File Structure

├── main.py              # Main game file
├── src/
│   └── utils.py              # Hand detection and prediction utilities
│   └── pretrained_model.pb   # TensorFlow frozen inference graph

---

🧪 Notes

• Ensure your webcam is working and well-lit
• You can adjust thresholds and chunk size in the FLAGS

---

📜 License

MIT License – use, modify, and play freely!

---

🤖 Inspired by

Gesture-based gaming, AI-powered interfaces, and classic Pong nostalgia.