A new approach for motion characterization in image sequences is presented. It relies on the probabilistic modeling of temporal and scale co-occurrence distributions of local motion-related measurements directly computed over image sequences. Temporal multiscale Gibbs models allow us to handle both spatial and temporal aspects of image motion content within a unified statistical framework. Since this modeling mainly involves the scalar product between co-occurrence values and Gibbs potentials, we can formulate and address several fundamental issues: model estimation according to the ML criterion (hence, model training and learning) and motion classification. We have conducted motion recognition experiments over a large set of real image sequences comprising various motion types such as temporal texture samples, human motion examples, and rigid motion situations.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Motion recognition using nonparametric image motion models estimated from temporal and multiscale co-occurrence statistics


    Beteiligte:
    Fablet, Ronan (Autor:in) / Bouthemy, P (Autor:in)

    Erscheinungsdatum :

    2003-12-01


    Anmerkungen:

    Ieee Transactions On Pattern Analysis And Machine Intelligence (0162-8828) (Ieee Computer Soc), 2003-12 , Vol. 25 , N. 12 , P. 1619-1624



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629




    Non Parametric Motion Recognition Using Temporal Multiscale Gibbs Models

    Fablet, R. / Bouthemy, P. / IEEE | British Library Conference Proceedings | 2001


    Learned Temporal Models of Image Motion

    Yacoob, Y. / Davis, L. / IEEE; Computer Society | British Library Conference Proceedings | 1998


    Qualitative Recognition of Motion Using Temporal Texture

    Nelson, R. C. / Polana, R. | British Library Online Contents | 1992


    Temporal co-occurrence matrix approaches to motion analysis [5298-26]

    Ukovich, A. / Koppen, M. / Ramponi, G. et al. | British Library Conference Proceedings | 2004