Person retrieval and indexing in video sequences is a challenging task for many multimedia applications. This paper proposes a new method that index the person based on the similarity. Firstly, the persons in a shot are detected and tracked through face detector and continuously adaptive mean shift algorithm. Then mid-level features such as clothes colors and voice are applied to represent the person. An unsupervised cluster method is performed to cluster the person for further indexing. At last, the cluster is validated and refined by the voice feature. Experimental results of proposed method are presented, and the method has been found to be effective.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Automatic Classification Video for Person Indexing


    Contributors:
    Peng, Jiang (author) / Lin, Qin Xiao (author)


    Publication date :

    2008-05-01


    Size :

    315826 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Video Preprocessing for Audiovisual Indexing

    Albiol, A. / Torres, L. / Delp, E. J. et al. | British Library Conference Proceedings | 2002


    Video preprocessing for audiovisual indexing

    Albiol, A. / Torres, L. / Delp, E.J. | IEEE | 2002


    Measuring the Motion Similarity in Video Indexing

    Hanis, A. / Sziranyi, T. / IEEE et al. | British Library Conference Proceedings | 2003


    Measuring the motion similarity in video indexing

    Hanis, A. / Sziranyi, T. | IEEE | 2003