2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings. (2003)
June 18, 2003 to June 20, 2003
Ahmed Elgammal , Rutgers University
Vinay Shet , University of Maryland
Yaser Yacoob , University of Maryland
Larry S. Davis , University of Maryland
This paper addresses the problem of capturing the dynamics for exemplar-based recognition systems. Traditional HMM provides a probabilistic tool to capture system dynamics and in exemplar paradigm, HMM states are typically coupled with the exemplars. Alternatively, we propose a non-parametric HMM approach that uses a discrete HMM with arbitrary states (decoupled from exemplars) to capture the dynamics over a large exemplar space where a nonparametric estimation approach is used to model the exemplar distribution. This reduces the need for lengthy and non-optimal training of the HMM observation model. We used the proposed approach for view-based recognition of gestures. The approach is based on representing each gesture as a sequence of learned body poses (exemplars). The gestures are recognized through a probabilistic framework for matching these body poses and for imposing temporal constraints between different poses using the proposed non-parametric HMM.
Y. Yacoob, L. S. Davis, V. Shet and A. Elgammal, "Learning Dynamics for Exemplar-based Gesture Recognition," 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.(CVPR), Madison, Wisconsin, 2003, pp. 571.