In this paper, a novel method to learn the intrinsic object structure for robust visual tracking is proposed. The basic assumption is that the parameterized object state lies on a low dimensional manifold and can be learned from training data. Based on this assumption, firstly we derived the dimensionality reduction and density estimation algorithm for unsupervised learning of object intrinsic representation, the obtained non-rigid part of object state reduces even to 2 dimensions. Secondly the dynamical model is derived and trained based on this intrinsic representation. Thirdly the learned intrinsic object structure is integrated into a particle-filter style tracker. We will show that this intrinsic object representation has some interesting properties and based on which the newly derived dynamical model makes particle-filter style tracker more robust and reliable. Experiments show that the learned tracker performs much better than existing trackers on the tracking of complex non-rigid motions such as fish twisting with self-occlusion and large inter-frame lip motion. The proposed method also has the potential to solve other type of tracking problems.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning object intrinsic structure for robust visual tracking


    Contributors:
    Qiang Wang, (author) / Guangyou Xu, (author) / Haizhou Ai, (author)


    Publication date :

    2003-01-01


    Size :

    418835 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Learning Object Intrinsic Structure for Robust Visual Tracking

    Wang, Q. / Xu, G. / Ai, H. et al. | British Library Conference Proceedings | 2003


    Incremental Learning for Robust Visual Tracking

    Ross, D. A. / Lim, J. / Lin, R. S. et al. | British Library Online Contents | 2008


    Learning structured visual dictionary for object tracking

    Yang, F. / Lu, H. / Yang, M. H. | British Library Online Contents | 2013


    SPiKeS: Superpixel-Keypoints structure for robust visual tracking

    Derue, F. o. / Bilodeau, G. A. / Bergevin, R. | British Library Online Contents | 2018


    Robust visual tracking based on deep sparse learning

    Wang, Xin / Hou, Zhiqiang / Yu, Wangsheng et al. | British Library Online Contents | 2017