Computer sensing of hand and limb motion is an important problem for applications in human-computer interaction, virtual reality, and athletic performance measurement. We describe a framework for local tracking of self-occluding motion, in which parts of the mechanism obstruct each others visibility to the camera. Our approach uses a kinematic model to predict occlusion and windowed templates to track partially occluded objects. We analyze our model of self-occlusion, discuss the implementation of our algorithm, and give experimental results for 3D hand tracking under significant amounts of self-occlusion. These results extend the DigitEyes system for articulated tracking described in [22, 21] to handle self-occluding motions. Contents 1 Introduction 1 2 A Framework for Tracking Self-Occluding Objects 2 2.1 Representing Self-Occlusion with Layered Templates : : : : : : : : : : : : : : 3 2.2 Local Visibility Orders for Templates : : : : : : : : : : : : : : : : : : : : : : 4 2.3 Wind...

. This paper describes techniques for the design of a system able to interact with the user by visual recognition of hand gestures. The system is composed of three modules including tracking, posture classification and gesture recognition. A description of each module is given. In order to increase the robustness and the precision of the tracking, several complementary tracking processes are coupled. A classification process is presented for recognizing hand posture using distance in an eigenspace. The classification of hand posture leads to the gesture recognition by a set of finite state machines. 1 Introduction Classical computer input devices are limited to keyboard and mouse. There is a growing interest in developing more intuitive and natural [10] interaction modes between user and computer. Hand gesture is a potentially rich communication channel between user and computer [2]. Symbolic information can be communicated using a gesture language [1]. Gesture is often included in Mu...