CourtCastAI 🏀

A real-time basketball court mapping system that transforms broadcast camera views into tactical top-down court visualizations.

🚀 Getting Started

Prerequisites

• Python 3.10 or higher
• CUDA-capable GPU (RTX 3060+ recommended)
• FFmpeg (for video/RTSP support)

Installation

1. Clone the repository:

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

2. Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies:

pip install -r requirements.txt

📁 Project Structure

CourtCastAI/
├── src/
│   ├── video/           # Video processing modules
│   ├── detection/       # Player detection modules
│   ├── tracking/        # Player tracking modules
│   ├── mapping/         # Court mapping modules
│   └── utils/           # Utility functions
├── tests/               # Test files
├── data/               # Data directory
│   ├── models/         # Pretrained models
│   └── videos/         # Sample videos
├── notebooks/          # Jupyter notebooks for development
└── config/            # Configuration files

🎯 Current Development Status

Currently in Phase 0 (P0): Project setup and basic pipeline development.

📝 License

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

👤 Author

Om Rode Computer Vision Engineer | Quantic Tech Analysis