We consider tracking as a binary classification problem, where an ensemble of weak classifiers is trained online to distinguish between the object and the background. The ensemble of weak classifiers is combined into a strong classifier using AdaBoost. The strong classifier is then used to label pixels in the next frame as either belonging to the object or the background, giving a confidence map. The peak of the map, and hence the new position of the object, is found using mean shift. Temporal coherence is maintained by updating the ensemble with new weak classifiers that are trained online during tracking. We show a realization of this method and demonstrate it on several video sequences.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Ensemble tracking


    Contributors:
    Avidan, S. (author)


    Publication date :

    2005-01-01


    Size :

    818260 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Clustering based ensemble correlation tracking

    Zhu, Guibo / Wang, Jinqiao / Lu, Hanqing | British Library Online Contents | 2016


    Clustering based ensemble correlation tracking

    Zhu, Guibo / Wang, Jinqiao / Lu, Hanqing | British Library Online Contents | 2016


    Clustering based ensemble correlation tracking

    Zhu, Guibo / Wang, Jinqiao / Lu, Hanqing | British Library Online Contents | 2016


    Markov Chain Monte Carlo Modular Ensemble Tracking

    Penne, T. / Tilmant, C. / Chateau, T. et al. | British Library Online Contents | 2013


    On-Line Ensemble SVM for Robust Object Tracking

    Tian, Min / Zhang, Weiwei / Liu, Fuqiang | Springer Verlag | 2007