Developer builds a computer vision tennis coach tracking ball speed and stroke form
measure_plan · x · 2026-09-09
@measureplan trained a computer vision model to coach his tennis game, tracking ball speed, forehand vs backhand strokes, shot placement, and body position at contact.
Pipeline details:
- Input video from an iPhone
- CV pipeline orchestrated with Roboflow Agent: data labeling via Astra 6, detection with a fine-tuned RF-DETR model
- Video annotation in Python + OpenCV
Next step: an app that records each practice session, tracks progress over time, and gives technique feedback.
More from coding & agent
- Greg Kamradt digs into gamedevbench: reference solutions edit 4.7 files, 114 lines on average — GregKamradt · 2026-09-10
- After Claude beat Pokemon FireRed, a harder benchmark built on ROM hack Radical Red — simonguozirui · 2026-09-10
- One prompt, full autonomous brand design: GPT Image's new sketch feature driven via Codex computer use — venturetwins · 2026-09-10
- Fireship built the same game with Astra and Fable 5.1 — only one was fun — Fireship · 2026-09-10
- How 3 founders and AI agents run a company with no employees or departments — AmosBarJoseph · 2026-09-10
- AI coding tool pricing is getting weird: the seat price is almost meaningless now — Informal-Dust4499 · 2026-09-10