One Hand Tracking Algorithm Based on Behavioral Model of Grasping Object and Particle Filter

A novel human hand tracking algorithm based on a single-view camera is put forward. First, we remove the deformity gesture before tracking employing hand physical constraint and motion constraint. Second, we get data from digital glove in the process of hand grasping object, then we obtain the polynomial law of joint motion by analyzing the data to reduce the dimension. Finally, we fuse the behavioral model and optimized particle filter to improve the result of tracking. The innovation of this paper is to establish the behavioral model of grasping object. The experiments show that the proposed algorithm can track movement of hand accurately and quickly.