AI-powered racing line analysis to find the fastest, most efficient path around any track
DriveOS is a deep learning application that trains neural networks to detect racing track boundaries in real-time video footage. Inspired by comma.ai's openpilot lane detection system, DriveOS uses advanced computer vision to understand track geometry from a driver's perspective.
- Download this repository (Code → Download ZIP)
- Extract to any location
- Double-click
INSTALL.bat
The installer automatically handles everything - Python environment, dependencies, GPU detection, and creates a desktop shortcut. Launch DriveOS from your desktop after installation!
Recommended:
- 16 GB RAM, 10 GB free space
- Intel Core i7/i9 or AMD Ryzen 7/9 (8+ cores)
- NVIDIA GPU (GTX 1060 6GB+, RTX 2060+) - 10-20x faster training
Process racing videos and overlay the optimal racing line.
Real time racing line analysis from video files, webcams, or screen capture.
Interactive annotation tool for creating custom training datasets.
Train custom AI models on your own racing footage.
This project is licensed under the MIT License - see the LICENSE file for details.
- "Python not found": Install Python 3.9-3.11, check "Add Python to PATH"
- Installation fails: Run as Administrator, check internet connection
- Slow processing: Close other apps, consider NVIDIA GPU for 10-20x speedup
- Issues/questions: GitHub Issues
- Contributions welcome via Pull Requests
Made with ❤️ for the racing community | DriveOS - Drive faster, smarter, better 🏁