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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning dynamics for exemplar-based gesture recognition


    Contributors:
    Elgammal, A. (author) / Shet, V. (author) / Yacoob, Y. (author) / Davis, L.S. (author)


    Publication date :

    2003-01-01


    Size :

    1303620 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Learning Dynamics for Exemplar-Based Gesture Recognition

    Elgammal, A. / Shet, V. / Yacoob, Y. et al. | British Library Conference Proceedings | 2003


    Dynamic hand gesture recognition: An exemplar-based approach from motion divergence fields

    Shen, X. / Hua, G. / Williams, L. et al. | British Library Online Contents | 2012


    Exemplar-based logo and trademark recognition

    Farajzadeh, N. | British Library Online Contents | 2015


    Exemplar-based tracking and recognition of arm gestures

    Elgammal, A. / Shet, V. / Yacoob, Y. et al. | IEEE | 2003


    Exemplar-Based Tracking and Recognition of Arm Gestures

    Elgammal, A. / Shet, V. / Yacoob, Y. et al. | British Library Conference Proceedings | 2003