This study by Yo Kobayashi and Yoshihiro Katagi from Osaka University aims to estimate wrist joint angles using ultrasound images. This method is expected to enhance the control performance of assistive devices and human-machine interfaces. The experiment involved obtaining joint angle information during extension flexion movements while acquiring ultrasound images of the muscles involved. A multivariate linear regression model was used to estimate the joint angles, with the coordinates of the feature points obtained through optical flow from the ultrasound images serving as explanatory variables. The model was trained and tested for each trial by each participant. The results suggest that the method offers a highly accurate estimation of joint angles compared to previous studies using other signals, like surface electromyography.
Publication date: 5 Jan 2024
Project Page: Not specified
Paper: https://arxiv.org/pdf/2401.02152
