How to make a simple and robust 3D hand tracking device using a single camera

In this paper we propose a non intrusive tracking system able to capture simple hand gestures in a fast and reliable way. Our device uses the images taken from a single camera to capture the 31) position and orientation of the hand of the user. In particular, the 3D position of the forefinger tip is used as a 31) marker, and the posture of the hand is used to input simple commands. The proposed approach combines several computer vision algorithms in order to exploit their strengths trying to minimize their drawbacks. The result is a real time system that is very robust against noise and cluttered backgrounds. An evaluation of the quality of the proposed approach is also presented.