Probabilistic models have been previously shown to be efficient and effective for modeling and recognition of human motion. In particular we focus on methods which represent the human motion model as a triangulated graph. Previous approaches learned models based just on positions and velocities of the body parts while ignoring their appearance. Moreover, a heuristic approach was commonly used to obtain translation invariance. In this paper we suggest an improved approach for learning such models and using them for human motion recognition. The suggested approach combines multiple cues, i.e., positions, velocities and appearance into both the learning and detection phases. Furthermore, we introduce global variables in the model, which can represent global properties such as translation, scale or view-point. The model is learned in an unsupervised manner from unlabelled data. We show that the suggested hybrid probabilistic model (which combines global variables, like translation, with local variables, like relative positions and appearances of body parts), leads to: (i) faster convergence of learning phase, (it) robustness to occlusions, and, (Hi) higher recognition rate.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Hybrid models for human motion recognition


    Contributors:
    Fanti, C. (author) / Zelnik-Manor, L. (author) / Perona, P. (author)


    Publication date :

    2005-01-01


    Size :

    383945 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Hybrid Dynamical Models of Human Motion for the Recognition of Human Gaits

    Bissacco, A. / Soatto, S. | British Library Online Contents | 2009


    Conditional models for contextual human motion recognition

    Sminchisescu, C. / Kanaujia, A. / Zhiguo Li, et al. | IEEE | 2005


    Conditional models for contextual human motion recognition

    Sminchisescu, C. / Kanaujia, A. / Metaxas, D. | British Library Online Contents | 2006