RTMPose
A real-time multi-person pose estimation framework developed by OpenMMLab. It outputs human keypoint coordinates at high frame rates, including pixel-level positions of joints such as shoulders, elbows, and wrists, and is widely applied in motion and action analysis scenarios.
Timeline (last 90 days)
The action recognition stage uses RTMPose for pose estimation, followed by a lightweight classifier to detect punches, capable of identifying the punching hand and distinguishing punch types.
RTMPose is a real-time multi-person pose estimation framework developed by OpenMMLab, capable of outputting human keypoint coordinates at high frame rates.
All Facts (2)
The action recognition stage uses RTMPose for pose estimation, followed by a lightweight classifier to detect punches, capable of identifying the punching hand and distinguishing punch types.
50%UnverifiedRTMPose is a real-time multi-person pose estimation framework developed by OpenMMLab, capable of outputting human keypoint coordinates at high frame rates.
50%