HAND TRACKING IN TIME-VARYING ILLWATION I-

.. Abstract: Tracking hand using a webeam in daily environment always suffers from limited dynamic range and changing light conditions. This paper presents a novel approach to generate steady hand segmentation f" the videos captured by a webcam in the lime-varying illumination. Our approach consists of two parts: automatic gain control (AGC) dnring capture and motion of skin distribution estimating. A Markov model is exploied to estimate and pdict the skin color distribution and camera parameters. We show that examples of segmented hand in a variety of lighting conditions. This method is used in our augmented reality map navigation system for bare band control. The experiment shows this process can run in real time and the error rate is acceptable.

[1]  E. Granum,et al.  Skin colour detection under changing lighting conditions , 1999 .

[2]  Dieter Schmalstieg,et al.  Finger tracking for interaction in augmented environments , 2001, Proceedings IEEE and ACM International Symposium on Augmented Reality.

[3]  Stan Sclaroff,et al.  Estimation and prediction of evolving color distributions for skin segmentation under varying illumination , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[4]  Andrew Blake,et al.  Learning dynamical models using expectation-maximisation , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[5]  François Bérard,et al.  Bare-hand human-computer interaction , 2001, PUI '01.

[6]  Tsuhan Chen,et al.  Hand tracking using spatial gesture modeling and visual feedback for a virtual DJ system , 2002, Proceedings. Fourth IEEE International Conference on Multimodal Interfaces.

[7]  Margrit Betke,et al.  Counting Fingers in Real Time: A Webcam-Based Human-Computer Interface with Game Applications , 2003, HCI.

[8]  Hans Jørgen Andersen,et al.  Estimation of the illuminant colour from human skin colour , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).