This paper presents a novel multiple collaborative kernel approach to visual tracking. This approach treats kernel-based tracking in a more general setting, i.e., a relaxation and constraints formulation, in which a complex motion is represented by a set of inter-correlated simpler motions. With this formulation, we present a rigorous analysis on a critical issue of kernel observability and obtain a criterion, based on which we propose a new method using collaborative kernels that has the theoretical guarantee of enhanced observability. This new method has been shown to be computationally efficient in both theory and practice, which can be readily applied to complex motions such as articulated motions.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Multiple collaborative kernel tracking


    Beteiligte:
    Zhimin Fan (Autor:in) / Ying Wu (Autor:in) / Ming Yang (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    704505 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Multiple Kernel Tracking with SSD

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


    Multiple kernel tracking with SSD

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


    Collaborative tracking of multiple targets

    Ting Yu, / Ying Wu, | IEEE | 2004


    Collaborative Tracking of Multiple Targets

    Yu, T. / Wu, Y. / IEEE Computer Society | British Library Conference Proceedings | 2004


    Multiple object tracking with kernel particle filter

    Cheng Chang, / Ansari, R. / Khokhar, A. | IEEE | 2005