A new particle filter, kernel particle filter (KPF), is proposed for visual tracking for multiple objects in image sequences. The KPF invokes kernels to form a continuous estimate of the posterior density function and allocates particles based on the gradient derived from the kernel density estimate. A data association technique is also proposed to resolve the motion correspondence ambiguities that arise when multiple objects are present. The data association technique introduces minimal amount of computation by making use of the intermediate results obtained in particle allocation. We show that KPF performs robust multiple object tracking with improved sampling efficiency.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multiple object tracking with kernel particle filter


    Contributors:
    Cheng Chang, (author) / Ansari, R. (author) / Khokhar, A. (author)


    Publication date :

    2005-01-01


    Size :

    685418 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Fast Multiple Object Tracking via a Hierarchical Particle Filter

    Yang, C. / Duraiswami, R. / Davis, L. et al. | British Library Conference Proceedings | 2005


    Fast multiple object tracking via a hierarchical particle filter

    Changjiang Yang, / Duraiswami, R. / Davis, L. | IEEE | 2005


    Multiple kernel tracking with SSD

    Hager, G.D. / Dewan, M. / Stewart, C.V. | IEEE | 2004


    Multiple Kernel Tracking with SSD

    Hager, G. / Dewan, M. / Stewart, C. et al. | British Library Conference Proceedings | 2004