Unverified50% confidenceFactExact time
The pipeline uses SAM 3 for object segmentation and tracking, identifying fighters and separately extracting the ring surface and ropes as pixel-level masks.
1
Sources
50%
Confidence
Long-term
Relevance
10/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA developer used vibe-coding to build an automated boxing event analysis pipeline that can track fighters, recognize punches, reconstruct top-down ring positions, and estimate real distances between fighters using only single-camera video.65% similarUnverifiedSAM's architecture consists of three components: a heavyweight image encoder based on Vision Transformer, a flexible prompt encoder, and a lightweight mask decoder.63% similarUnverified工作流中的抠图节点依赖语义分割模型（如SAM、U²-Net等），能够自动识别图像中的主体对象并去除背景，输出带透明通道的PNG图像63% similarUnverifiedThe pipeline uses the ring mask to fit a ring model, mapping pixel positions in the frame to top-down view coordinates.62% similarUnverifiedSAM 3 allows decoupling visual encoding from text conditioning; by reusing visual embeddings via get_vision_features to avoid re-encoding the image for each category, it delivers close to N-fold speedup on multi-category tasks.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/980576API
curl https://kongchang.com/api/v1/knowledge/claims/980576MCP
get_claim(id=980576)