Stereo Vision Based Position Measurement Feedback for a Functional Electrical Stimulation Control System

摘要

The problem of image based position measurement of a moving object is addressed in this paper. We show that based on corresponding features, the position of the object can be measured by a pair of images from a stereo camera system and the motion can be predicted based on previous observations. The position measurement and prediction information can then be used as feedback in a closed loop control system to improve the control of a functional electrical stimulation (FES) system. We show how markers can be used to measure the position of a robot gripper and skin color can be used to measure position of a human hand in an application. We then show how the motion of a hand model can be recovered based on the measurements and how the motion can be simulated and predicted. The position measurement and motion identification methods are verified by the presentation of experimental results obtained using the methods described in the paper.