Markerless motion capture of hands and fingers in high-speed throwing task and its accuracy verification

Abstract

In human motion capture systems, reflective markers attached to the body have been widely used to track motion using optical cameras. However, when the speed of motion increases, because the brightness and angle of view of the camera are limited, and the markers often fall off, particularly of detailed body parts such as fingers in full-body movements, other parts of the body (palms) have been investigated. This study attempted to acquire finger movements during a high-speed throwing task without attaching markers using automatic image recognition technology based on deep learning (DeepLabCut) and verified its accuracy compared to conventional methods. As a result, the absolute distance between the 3D coordinates obtained from the two motion capture systems was an average of 15.5 to 29.4 mm depending on tracked points, and the correlation coefficients between them ranged from 0.932 to 0.999. Therefore, the shapes of the time-series profiles of the 3D coordinates obtained from the two motion- capture systems were similar. These results suggest that motion measurement using markerless motion capture is possible in environments where conventional motion capture systems are difficult to use.