3D hand posture tracking with depth gradient estimation on a RGB-D camera

This paper presents a real-time 3D hand posture estimation using the data from a RGB-D camera. A hierarchical method is adopted to first estimate the pose of palm and then the pose of fingers. The particle filtering algorithm with efficient particle generation for tracking the palm and fingers is proposed by analyzing the depth gradient and the contour of hand region. The finger motion model with chain reaction is also constructed to predict the hand pose transition feasibly.