Region-based tracking in a temporal image sequence is described as a segmentation of current frame into a set of non-overlapping regions: the tracking regions and the non-tracking region. The segmentation is viewed to be a Markov labeling process. Based on the key idea of using a doubly stochastic prior model, the optimal estimation for the label field is found by the minimization of a differentiable function. We exploit the feature-spatial probabilistic representation of a region as the conditional distribution in the Bayesian framework, which makes our tracker robust to local deformation and partial occlusion. The continuity of the objective function leads to a much faster numerical implementation. Very promising experimental results on some real-world sequences are presented to illustrate the performance of the presented algorithm.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Region Tracking via HMMF in Joint Feature-Spatial Space


    Contributors:


    Publication date :

    2005-01-01


    Size :

    283826 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Probabilistic tracking in joint feature-spatial spaces

    Elgammal, A. / Duraiswami, R. / Davis, L.S. | IEEE | 2003


    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