A usable real-time 3D hand tracker

Abstract

This paper presents a computer vision system for tracking human hands. The algorithms used to extract the 3D position, and planar orientation of the hand, and the joint angles of the fingers are described. The combined system is able to track a natural hand at 30 frames per second on a standard workstation with no special image processing hardware other than a frame grabber. The tracker has been used as an interface for navigating around virtual worlds.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>