Real-time Hand Tracking Using Kinect

Abstract

Real-time hand tracking is fundamental to human gesture recognition. However, due to the huge computation, previous studies are either off-line or limited to given poses. In order to satisfy the requirement of real-time hand tracking, in this paper we propose a real time hand tracking method using Kinect. Firstly we extract the hand region from the depth image output from Kinect. Then we achieve the hand parameters. During the procedure of hand region extraction, we propose a cascade structure with recursive connected component algorithm to improve the efficiency and reserve connection relationships in 3D space. To determine the fingertips, we use the former 3D connections and geodesic distance over hand skeleton pixels to guarantee the accuracy and robustness, with acceptable loss. Experimental results show that our proposed solution can significantly improve the quality of real-time hand tracking.