Most gait recognition approaches only study human walking frontoparallel to the image plane which is not realistic in video surveillance applications. Human gait appearance depends on various factors including locations of the camera and the person, the camera axis and the walking direction. By analyzing these factors, we propose a statistical approach for view-insensitive gait recognition. The proposed approach recognizes human using a single camera, and avoids the difficulties of recovering the human body structure and camera calibration. Experimental results show that the proposed approach achieves good performance in recognizing individuals walking along different directions.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A study on view-insensitive gait recognition


    Beteiligte:
    Ju Han, (Autor:in) / Bir Bhanu, (Autor:in) / Roy-Chowdhury, A.K. (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    169252 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    A Study on View-Insensitive Gait Recognition

    Han, J. / Bhanu, B. / Roy-Chowdhury, A. K. | British Library Conference Proceedings | 2005



    Illumination insensitive recognition using eigenspaces

    Bischof, H. / Wildenauer, H. / Leonardis, A. | British Library Online Contents | 2004


    Gait Recognition Using a View Transformation Model in the Frequency Domain

    Makihara, Yasushi / Sagawa, Ryusuke / Mukaigawa, Yasuhiro et al. | Springer Verlag | 2006

    Freier Zugriff

    Gait Recognition Using a View Transformation Model in the Frequency Domain

    Makihara, Y. / Sagawa, R. / Mukaigawa, Y. et al. | British Library Conference Proceedings | 2006