This paper proposes a visual tracking algorithm that combines motion and appearance in a statistical framework. It is assumed that image observations are generated simultaneously from a background model and a target appearance model. This is different from conventional appearance-based tracking, that does not use motion information. The proposed algorithm attempts to maximize the likelihood ratio of the tracked region, derived from appearance and background models. Incorporation of motion in appearance based tracking provides robust tracking, even when the target violates the appearance model. We show that the proposed algorithm performs well in tracking targets efficiently over long time intervals.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Tracking objects in video using motion and appearance models


    Contributors:


    Publication date :

    2005-01-01


    Size :

    525917 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Tracking Objects in Video using Motion and Appearance Models

    Sankaranarayanan, A. C. / Chellappa, R. / Zheng, Q. | British Library Conference Proceedings | 2005


    Accurate 3D Tracking of Rigid Objects with Occlusion Using Active Appearance Models

    Mittrapiyanuruk, Pradit / DeSouza, Guilherme N. / Kak, Avinash C. | IEEE | 2005


    Tracking video objects using active contours

    Castaud, M. / Barlaud, M. / Aubert, G. | IEEE | 2002


    Tracking Video Objects Using Active Contours

    Gastaud, M. / Barlaud, M. / Aubert, G. | British Library Conference Proceedings | 2002