Since the appearance changes of the target jeopardize visual measurements and often lead to tracking failure in practice, trackers need to be adaptive to non-stationary appearances or to dynamically select features to track. However, this idea is threatened by the risk of adaptation drift that roots in its ill-posed nature, unless good constraints are imposed. Different from most existing adaptation schemes, we enforce three novel constraints for the optimal adaptation: (1) negative data, (2) bottom-up pair-wise data constraints, and (3) adaptation dynamics. Substantializing the general adaptation problem as a subspace adaptation problem, this paper gives a closed-form solution as well as a practical iterative algorithm. Extensive experiments have shown that the proposed approach can largely alleviate adaptation drift and achieve better tracking results.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Tracking non-stationary appearances and dynamic feature selection


    Contributors:
    Yang, M. (author) / Wu, Y. (author)


    Publication date :

    2005-01-01


    Size :

    911359 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Tracking Appearances with Occlusions

    Wu, Y. / Yu, T. / Hua, G. et al. | British Library Conference Proceedings | 2003


    Tracking appearances with occlusions

    Ying Wu, / Ting Yu, / Gang Hua, | IEEE | 2003


    Corresponding dynamic appearances

    Gong, S. / Psarrou, A. / Romdhani, S. | British Library Online Contents | 2002


    USER INTERFACES WITH VARIABLE APPEARANCES

    DELLINGER RICHARD R | European Patent Office | 2022

    Free access

    Factorized appearances for object detection

    Gonfaus, J.M. / Pedersoli, M. / Gonzalez, J. et al. | British Library Online Contents | 2015