# DeepCourt

- **Event:** [Gemini 3 SuperHack](https://cerebralvalley.ai/e/gemini-3-superhack)
- **When:** Sat, Jan 31 at 9:00 AM – 10:00 PM (PST)
- **Where:** 365 Toni Stone Xing, San Francisco, CA
- **Team:** [Y Liu](https://cerebralvalley.ai/u/snapfinger), [Yueyan Gu](https://cerebralvalley.ai/u/yueyangu), [Wenxuan Hu](https://cerebralvalley.ai/u/wenxuanhu)
- **GitHub:** https://github.com/snapfinger/DeepCourt
- **Demo video:** https://youtu.be/9souIjHBeOU
- **Gallery:** https://cerebralvalley.ai/e/gemini-3-superhack/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/gemini-3-superhack/hackathon/gallery/44

DeepCourt turns any camera into a real-time sports intelligence system. No sensors. No wearables. No waiting - just elite analytics while the game is still on.

Powered by Gemini’s high-speed vision, Rally Mode analyzes live or uploaded video every 750ms to map player positions, track shot trajectories, and reveal rally patterns - delivering role-specific tactical cues for coaches, players, and opponent exploitation in near real time.

Posture Mode breaks down biomechanics from uploaded footage, evaluating balance, footwork, power, and technique. It highlights strengths and weaknesses, recommends targeted drills, and compares performance to pro benchmarks - visualized through radar charts and concise summaries.

---

Markdown version of https://cerebralvalley.ai/e/gemini-3-superhack/hackathon/gallery/44. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt