We present a method for evaluating multiple feature spaces while tracking, and for adjusting the set of features used to improve tracking performance. Our hypothesis is that the features that best discriminate between object and background are also best for tracking the object. We develop an online feature selection mechanism based on the two-class variance ratio measure, applied to log likelihood distributions computed with respect to a given feature from samples of object and background pixels. This feature selection mechanism is embedded in a tracking system that adaptively selects the top-ranked discriminative features for tracking. Examples are presented to illustrate how the method adapts to changing appearances of both tracked object and scene background.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    On-line selection of discriminative tracking features


    Contributors:
    Collins, (author) / Liu, (author)


    Publication date :

    2003-01-01


    Size :

    601000 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    On-Line Selection of Discriminative Tracking Features

    Collins, R. / Liu, Y. / IEEE | British Library Conference Proceedings | 2003


    Online selecting discriminative tracking features using particle filter

    Jianyu Wang, / Xilin Chen, / Wen Gao, | IEEE | 2005


    Online selection of discriminative pixel-pair feature for tracking

    Nishida, Kenji / Kurita, Takio / Higashikubo, Masakatsu | Tema Archive | 2010


    Discriminative Mean Shift Tracking with Auxiliary Particles

    Wang, Junqiu / Yagi, Yasushi | Springer Verlag | 2007


    Multi-object tracking via discriminative appearance modeling

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