Unverified50% confidenceFactExact time
Human detection is usually based on lightweight object detection models (such as the YOLO series or vendors' in-house models), running on the camera or on a local NVR.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA developer built a javelin throw analysis system based on YOLO11 that can automatically detect javelins from television broadcast footage, track athlete movements, calculate joint angles, identify throwing phases, and plot flight trajectories.70% similarUnverifiedFigure's robots and Tesla's Optimus are being tested on tasks such as sorting and simple assembly, using vision-language-action models to map camera images and voice commands into action sequences.65% similarUnverifiedTraditional 2D detectors (such as YOLO and DETR series) are trained on planar images and output bounding boxes in image pixel coordinates, which carry no spherical geometric information.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1073486API
curl https://kongchang.com/api/v1/knowledge/claims/1073486MCP
get_claim(id=1073486)