![[OC] Player Tracking, Team Detection, and Number Recognition](https://www.europesays.com/wp-content/uploads/2025/12/33200k0f9d5g1-1080x1024.png)
resources: youtube, code, blog
– player and number detection with RF-DETR
– player tracking with SAM2
– team clustering with SigLIP, UMAP and K-Means
– number recognition with SmolVLM2
– perspective conversion with homography
– player trajectory correction
– shot detection and classification
Posted by RandomForests92
4 comments
VERY Cool. Thank you for sharing!
Wow this is awesome. Saved to watch and read later when I’m bored at work 😂
Damn, I thought this would be a video. Still way too cool though.
This is great. This would definitely help people learn what is happening on any given play. The broadcast angle makes it difficult to understand what’s happening and why.
They do this with the NFL, which is more complex but basketball is a faster game.
Comments are closed.