Gesture analysis for human-robot interaction

This paper is to present gesture analysis for human-robot interaction. Gesture analysis is consisted of four processes such as detecting of hand in bimanual movements, splitting of a meaning gesture region from image stream, extracting features and recognizing gesture. Skin color analysis, image motion detection and shape information are used to detect bimanual hand movements and gesture spotting. Skin color information for tracking hand gesture is obtained from face detection region. The velocity of moving hand is calculated for detecting a meaning gesture region from consecutive image frames. Combined gesture features such as structural and statistical features are extracted from image stream. We have experimented to evaluate detection of bimanual hand movements and gesture recognition with a camera, which is pan/tilt and a single camera that is mounted on mobile robot. Performance evaluation of gesture recognition has experimented using ETRI database and an encouraging recognition rate of 89 % has been obtained