In this paper, we present a novel visual object tracking algorithm based on ensemble of linear SVM classifiers. There are two main contributions in this paper. First of all, we propose a simple yet effective way for on-line updating linear SVM classifier, where useful “Key Frames” of target are automatically selected as support vectors. Secondly, we propose an on-line ensemble SVM tracker, which can effectively handle target appearance variation. The proposed algorithm makes better usage of history information, which leads to better discrimination of target and the surrounding background. The proposed algorithm is tested on many video clips including some public available ones. Experimental results show the robustness of our proposed algorithm, especially under large appearance change during tracking.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    On-Line Ensemble SVM for Robust Object Tracking


    Contributors:
    Yagi, Yasushi (editor) / Kang, Sing Bing (editor) / Kweon, In So (editor) / Zha, Hongbin (editor) / Tian, Min (author) / Zhang, Weiwei (author) / Liu, Fuqiang (author)

    Conference:

    Asian Conference on Computer Vision ; 2007 ; Tokyo, Japan November 18, 2007 - November 22, 2007


    Published in:

    Computer Vision – ACCV 2007 ; Chapter : 33 ; 355-364


    Publication date :

    2007-01-01


    Size :

    10 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Robust Observations for Object Tracking

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


    Robust observations for object tracking

    Bohyung Han, / Davis, L. | IEEE | 2005


    Ensemble tracking

    Avidan, S. | IEEE | 2005


    Object Centred Optimisation Process for Robust Multiple Object Tracking

    Connor, B. / Humphreys, D. K. P. / Smith, C. et al. | British Library Conference Proceedings | 1999


    Robust Environmental Perception of Multi-object Tracking

    Pan, Huihui / Wang, Jue / Yu, Xinghu et al. | Springer Verlag | 2023