A Tele-operated Gesture Recognition Mobile Robot using a Stereo Vision

In this paper, a tele-operated gesture recognition mobile robot using a stereo vision is represented. We propose a real-time face and hand classification and 3D position extraction using a stereo vision embedded system. To obtain the disparity image, we used the stereo vision process on FPGA and developed the embedded system to obtain the image sequence for basic image processing. Then we applied the simple and reliable algorithm we developed to detect and classify the head and hand in real-time on Tele-operation server. The arm posture and hand trajectory were used for gesture recognition. We also show the experimental result to support validity of the system and the algorithm.