In this paper we present a model based method for fast face orientation estimation and pose recovery from a monocular image sequence captured by an uncalibrated camera. To accomplish this method, CANDIDE-3 model is used to construct 3D individual face model manually. Four facial feature points (outer corners of eyes and mouth) are tracked by SIFT algorithm. Taking advantage of these feature points and 3D individual face model, facial pose recovery can be quickly completed with a Fast Face Orientation Estimation Algorithm. An experimental system has been built to carry out the estimation method. The estimation results are robust and flexible.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Fast Face Orientation Estimation from an Uncalibrated Monocular Camera


    Beteiligte:
    Wang, Xunheng (Autor:in) / Huang, Haiqing (Autor:in) / Ruan, Zongcai (Autor:in) / Lu, Zuhong (Autor:in)


    Erscheinungsdatum :

    2008-05-01


    Format / Umfang :

    481084 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Robust Position Estimation Using Images From an Uncalibrated Camera

    Doehler, H.-U. / IEEE / AIAA | British Library Conference Proceedings | 2003


    3D Face pose estimation and tracking from a monocular camera

    Ji, Q. | British Library Online Contents | 2002



    Recursive Estimation of Camera Motion from Uncalibrated Image Sequences

    Soatto, S. / Perona, P. / IEEE; Signal Processing Society | British Library Conference Proceedings | 1994


    Pedestrian Orientation Estimation using On-board Monocular Camera with Semi-Supervised Learning

    Yano, S. / Gu, Y. / Kamijo, S. et al. | British Library Conference Proceedings | 2014