Decomposable triangulated graphs have been shown to be efficient and effective for modeling the probabilistic spatio-temporal structure of brief stretches of human motion. In previous work such model structure was handcrafted by expert human observers and labeled data were needed for parameter learning. We present a method to build automatically the structure of the decomposable triangulated graph from unlabeled data. It is based on maximum-likelihood. Taking the labeling of the data as hidden variables, a variant of the EM algorithm can be applied. A greedy algorithm is developed to search for the optimal structure of the decomposable model based on the (conditional) differential entropy of variables. Our algorithm is demonstrated by learning models of human motion completely automatically from unlabeled real image sequences with clutter and occlusion. Experiments on both motion captured data and grayscale image sequences show that the resulting models perform better than the hand-constructed models.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning probabilistic structure for human motion detection


    Beteiligte:
    Song, Y. (Autor:in) / Goncalves, L. (Autor:in) / Perona, P. (Autor:in)


    Erscheinungsdatum :

    2001-01-01


    Format / Umfang :

    751268 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Learning Probabilistic Structure for Human Motion Detection

    Song, Y. / Goncalves, L. / Perona, P. et al. | British Library Conference Proceedings | 2001


    Probabilistic Parameter-Free Motion Detection

    Veit, T. / Cao, F. / Bouthemy, P. et al. | British Library Conference Proceedings | 2004


    Probabilistic parameter-free motion detection

    Veit, T. / Cao, F. / Bouthemy, P. | IEEE | 2004


    Probabilistic Detection and Tracking of Motion Boundaries

    Black, M. J. / Fleet, D. J. | British Library Online Contents | 2000


    Dynamically consistent probabilistic model for robot motion learning

    Pardo Ayala, Diego Esteban / Rozo Castañeda, Leonel / Alenyà Ribas, Guillem et al. | BASE | 2012

    Freier Zugriff