Binocular Hand Tracking and Reconstruction Based on 2D Shape Matching

This paper presents a method for real-time 3D hand tracking in images acquired by a calibrated, possibly moving stereoscopic rig. The proposed method consists of a collection of techniques that enable the modeling and detection of hands, their temporal association in image sequences, the establishment of hand correspondences between stereo images and the 3D reconstruction of their contours. Building upon our previous research on color-based, 2D skin-color tracking, the 3D hand tracker is developed through the coupling of the results of two 2D skin-color trackers that run independently on the two video streams acquired by a stereoscopic system. The proposed method runs in real time on a conventional Pentium 4 processor when operating on 320times240 images. Representative experimental results are also presented