This paper presents a practical technique for model-based 3D hand tracking. An anatomically accurate hand model is built from truncated quadrics. This allows for the generation of 2D profiles of the model using elegant tools from projective geometry, and for an efficient method to handle self-occlusion. The pose of the hand model is estimated with an Unscented Kalman filter (UKF), which minimizes the geometric error between the profiles and edges extracted from the images. The use of the UKF permits higher frame rates than more sophisticated estimation methods such as particle filtering, whilst providing higher accuracy than the extended Kalman filter The system is easily scalable from single to multiple views, and from rigid to articulated models. First experiments on real data using one and two cameras demonstrate the quality of the proposed method for tracking a 7 DOF hand model.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Model-based 3D tracking of an articulated hand


    Beteiligte:
    Stenger, B. (Autor:in) / Mendonca, P.R.S. (Autor:in) / Cipolla, R. (Autor:in)


    Erscheinungsdatum :

    01.01.2001


    Format / Umfang :

    609230 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Model-Based 3D Tracking of an Articulated Hand

    Stenger, B. / Mendonca, P. R. S. / Cipolla, R. et al. | British Library Conference Proceedings | 2001


    Model-based articulated hand motion tracking for gesture recognition

    Lien, C.-C. / Huang, C.-L. | British Library Online Contents | 1998


    Tracking Articulated Hand Underlying Graphical Model with Depth Cue

    Liu, Tangli / Liang, Wei / Wu, Xinxiao et al. | IEEE | 2008


    Appearance-guided particle filtering for articulated hand tracking

    Wen-Yan Chang, / Chu-Song Chen, / Yi-Ping Hung, | IEEE | 2005