科研之友
微信
新浪微博
Facebook
分享链接
摘要
Augmented Reality (AR)-assisted exercises for the enhancement of finger functions have been developed for many years and have proven to be effective. Most applications tracked the motion of upper-extremity using handheld trackers, which are not convenient to put on and take off. Bare-hand tracking algorithms have been utilized to address this limitation; however, only few AR-assisted healthcare approaches have been designed to train upper-extremity skills using bare-hand tracking, and even fewer approaches detect the Range of Motion (ROM) of fingers with low-cost devices. This paper presents a low-cost and multi-modal residential-based AR-assisted therapeutic healthcare exercise system. A computer vision-based bare-hand interaction method is proposed in this system. This method is designed to estimate finger bending degrees through their projection lengths. With an accurate feature detection strategy, this method is able to detect the full ROM using two web cameras. This system also incorporates a vibration wrist band to stimulate the users with tactile feedback, and an assessment module to evaluate user performance.
- 出版日期2016
