Visual tracking could be treated as a parameter estimation problem of target representation based on observations in image sequences. A richer target representations would incur better chances of successful tracking in cluttered and dynamic environments. However, the dimensionality of target's state space also increases making tracking a formidable estimation problem. In this paper, the problem of tracking and integrating multiple cues is formulated in a probabilistic framework; and represented by factorized graphical model. Structured variational analysis of such graphical model factorizes different modalities and suggests a co-inference process among these modalities. A sequential Monte Carlo algorithm is proposed to give an efficient approximation of the co-inference based on the importance sampling technique. This algorithm is implemented in real-time at around 30 Hz. Specifically, tracking both position, shape and color distribution of a target is investigated in this paper. Our extensive experiments show that the proposed algorithm performs robustly in a large variety of trucking scenarios. The approach presented in this paper has the potential to solve other sensor fusion problems.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A co-inference approach to robust visual tracking


    Beteiligte:
    Ying Wu, (Autor:in) / Huang, T.S. (Autor:in)


    Erscheinungsdatum :

    01.01.2001


    Format / Umfang :

    1006760 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    A Co-inference Approach to Robust Visual Tracking

    Wu, Y. / Huang, T. / IEEE | British Library Conference Proceedings | 2001


    Variational inference for visual tracking

    Vermaak, J. / Lawrence, N.D. / Perez, P. | IEEE | 2003


    Variational Inference for Visual Tracking

    Vermaak, J. / Lawrence, N. / Perez, P. et al. | British Library Conference Proceedings | 2003


    Robust Visual Tracking by Integrating Multiple Cues Based on Co-Inference Learning

    Wu, Y. / Huang, T. S. | British Library Online Contents | 2004


    A fuzzy inference approach to template-based visual tracking

    Ramirez-Paredes, J. P. | British Library Online Contents | 2012