This paper presents a system that can automatically recognize four different static human body postures in video sequences. The considered postures are standing, sitting, squatting, and lying. The recognition is based on data fusion using the belief theory. The data come from the persons 2D segmentation and from their face localization. It consists in distance measurements relative to a reference posture ("Da Vinci posture": standing, arms stretched horizontally). The segmentation is based on an adaptive background removal algorithm. The face localization process uses skin detection based on color information with an adaptive thresholding. The efficiency and the limits of the recognition system are highlighted thanks to the analysis of a great number of results. This system allows real-time processing.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Static human body postures recognition in video sequences using the belief theory


    Beteiligte:
    Girondel, V. (Autor:in) / Bonnaud, L. (Autor:in) / Caplier, A. (Autor:in) / Rombaut, M. (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    400141 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Static Human Body Postures Recognition in Video Sequences using the Belief Theory

    Girondel, V. / Bonnaud, L. / Caplier, A. et al. | British Library Conference Proceedings | 2005


    Template-based Recognition of Static Sitting Postures

    Zhu, Manli / Martinez, Aleix M. / Tan, Hong Z. | IEEE | 2003


    Virtual Scene Control Using Human Body Postures

    Yonemoto, Satoshi / Taniguchi, Rin-ichiro | IEEE | 2003


    Optimal Postures and Positioning for Human Body Scanning

    Brunsman, M. / Daanen, H. / Robinette, K. et al. | British Library Conference Proceedings | 1997


    Optimal postures and positioning for human body scanning

    Brunsman, M.A. / Daanen, H.M. / Robinette, K.M. | IEEE | 1997