Object tracking is a challenging problem in real-time computer vision due to variations of lighting condition, pose, scale, and view-point over time. However, it is exceptionally difficult to model appearance with respect to all of those variations in advance; instead, on-line update algorithms are employed to adapt to these changes. We present a new on-line appearance modeling technique which is based on sequential density approximation. This technique provides accurate and compact representations using Gaussian mixtures, in which the number of Gaussians is automatically determined. This procedure is performed in linear time at each time step, which we prove by amortized analysis. Features for each pixel and rectangular region are modeled together by the proposed sequential density approximation algorithm, and the target model is updated in scale robustly. We show the performance of our method by simulations and tracking in natural videos.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    On-line density-based appearance modeling for object tracking


    Contributors:
    Han, B. (author) / Davis, L. (author)


    Publication date :

    2005-01-01


    Size :

    708978 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    On-Line Density-Based Appearance Modeling for Object Tracking

    Han, B. / Davis, L. / IEEE | British Library Conference Proceedings | 2005


    Multi-object tracking via discriminative appearance modeling

    Huang, Shucheng / Jiang, Shuai / Zhu, Xia | British Library Online Contents | 2016


    Multi-object tracking via discriminative appearance modeling

    Huang, Shucheng / Jiang, Shuai / Zhu, Xia | British Library Online Contents | 2016


    Multi-object tracking via discriminative appearance modeling

    Huang, Shucheng / Jiang, Shuai / Zhu, Xia | British Library Online Contents | 2016


    Object tracking via appearance modeling and sparse representation

    Chen, F. / Wang, Q. / Wang, S. et al. | British Library Online Contents | 2011