Real-time chess tracking from iPhone video with RF-DETR and Stockfish
measure_plan · x · 2026-11-13
The author trained a computer vision model that tracks live chess games from iPhone video and feeds board state into Stockfish for real-time analysis.
Pipeline: video captured on iPhone; CV pipeline and training done via Roboflow MCP; data auto-labelled with Gemini; an RF-DETR model trained for realtime inference; moves and board state fed to Stockfish for live eval; video annotation with Python and OpenCV.
More from coding & agent
- Dev builds typing game where your keystrokes play the music, in 3 days with Fable — vauvva · 2026-11-13
- $10k Claude-powered 'Business Brain' install nets client $41.5k in 30 days — aryanXmahajan · 2026-11-13
- Wolfram Alpha MCP Server brings computational knowledge engine to AI agents — modelcontextprotocol · 2026-11-13
- What changes when 8 people share AI agents instead of each running their own — One-Wolverine-6207 · 2026-11-13
- Visual AI agents should save discovered pipelines as reusable programs, argues dev — prateekj · 2026-11-13
- AGENTS.md is the ask, not the check: every rule should be backed by a gate — therealdanvega · 2026-11-13