Video Motion Capture from the Part Confidence Maps of Multi-Camera Images by Spatiotemporal Filtering Using the Human Skeletal Model
This work addresses motion capture for human motion analysis, presenting an incremental improvement in accuracy and smoothness.
The paper tackled 3D human motion reconstruction from multi-camera images using a spatiotemporal filter based on Part Confidence Maps, achieving a mean per joint position error of 26.1mm for regular motions and 38.8mm for inverted motions.
This paper discusses video motion capture, namely, 3D reconstruction of human motion from multi-camera images. After the Part Confidence Maps are computed from each camera image, the proposed spatiotemporal filter is applied to deliver the human motion data with accuracy and smoothness for human motion analysis. The spatiotemporal filter uses the human skeleton and mixes temporal smoothing in two-time inverse kinematics computations. The experimental results show that the mean per joint position error was 26.1mm for regular motions and 38.8mm for inverted motions.