Learning dynamics for exemplar-based gesture recognition

TitleLearning dynamics for exemplar-based gesture recognition
Publication TypeConference Papers
Year of Publication2003
AuthorsElgammal A, Shet V, Yacoob Y, Davis LS
Conference NameComputer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on
Date Published2003/06//
Keywordsarbitrary, body, by, Computer, constraint;, detection;, discrete, distribution, dynamics;, edge, estimation;, example;, exemplar, exemplar-based, extraction;, feature, framework;, gesture, gesture;, hidden, HMM;, human, image, learning, Markov, matching;, model;, models;, motion;, nonparametric, pose, probabilistic, recognition;, sequence;, space;, state;, statistics;, system, temporal, tool;, view-based, vision;

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.