AI quantifies pickleball players from phone video: pose tracking and shot counting
Scobleizer · x · 2026-10-07
Qazi Ammar Arshad (ML Bench) demoed an AI that quantifies pickleball players from smartphone video: it detects and tracks players, estimates full-body pose, measures elbow/shoulder/hip/knee angles and stance width, and counts shots via ball detection. The main open challenge is converting video noise into reliable metrics.
More from Apps
- Mamanoko's audio doubles as a basic Japanese learning module — TarlonKhoubyari · 2026-10-07
- Amazon's new AI feature that summarizes everything it knows about you goes viral — venturetwins · 2026-10-07
- Meta formalizes personal-agent mediated recommendation, releases MediateRec benchmark — meta · 2026-10-07
- Bops launches business-ops AI agents, each with its own computer, email and phone number — alexcovo_eth · 2026-10-07
- Creator's 10-minute AI skill-made video hits 170K views overnight — AlchainHust · 2026-10-07
- Spawn Launches Monetization for AI-Generated Games: Sell Skins or Free Trial Unlocks — TAbrodi · 2026-10-07