In this paper, we present a probabilistic framework for tracking regions based on their appearance. We exploit the feature-spatial distribution of a region representing an object as a probabilistic constraint to track that region over time. The tracking is achieved by maximizing a similarity-based objective function over transformation space given a nonparametric representation of the joint feature-spatial distribution. Such a representation imposes a probabilistic constraint on the region feature distribution coupled with the region structure, which yields an appearance tracker that is robust to small local deformations and partial occlusion. We present the approach for the general form of joint feature-spatial distributions and apply it to tracking with different types of image features including row intensity, color and image gradient.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Probabilistic tracking in joint feature-spatial spaces


    Beteiligte:
    Elgammal, A. (Autor:in) / Duraiswami, R. (Autor:in) / Davis, L.S. (Autor:in)


    Erscheinungsdatum :

    2003-01-01


    Format / Umfang :

    1017783 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Probabilistic Tracking in Joint Feature-Spatial Spaces

    Elgammal, A. / Duraiswami, R. / Davis, L. et al. | British Library Conference Proceedings | 2003


    Joint Feature-Spatial-Measure Space: A New approach to Highly Efficient Probabilistic Object Tracking

    Chen, F. / Yuan, X. / Yang, S. | British Library Conference Proceedings | 2005



    Region Tracking via HMMF in Joint Feature-Spatial Space

    XiaoTong, Yuan / ShuTang, Yang / HongWen, Zhu | IEEE | 2005


    Feature-based probabilistic data association and tracking

    Grinberg,M. / Ohr,F. / Beyerer,J. et al. | Kraftfahrwesen | 2010