In this paper we propose a log likelihood-ratio function of foreground and background models used in a particle filter to track the eye region in dark-bright pupil image sequences. This model fuses information from both dark and bright pupil images and their difference image into one model. Our enhanced tracker overcomes the issues of prior selection of static thresholds during the detection of feature observations in the bright-dark difference images. The auto-initialization process is performed using cascaded classifier trained using adaboost and adapted to IR eye images. Experiments show good performance in challenging sequences with test subjects showing large head movements and under significant light conditions.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Improved Likelihood Function in Particle-based IR Eye Tracking


    Beteiligte:
    Witzner Hansen, D. (Autor:in) / Satria, R. (Autor:in) / Sorensen, J. (Autor:in) / Hammoud, R. (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    393253 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    An improved likelihood model for eye tracking

    Hansen, D. W. / Hammoud, R. I. | British Library Online Contents | 2007



    On-Road Multivehicle Tracking Using Deformable Object Model and Particle Filter With Improved Likelihood Estimation

    Tehrani Niknejad, Hossein / Takeuchi, Akihiro / Mita, Seiichi et al. | IEEE | 2012



    Tracking human motion using auxiliary particle filters and iterated likelihood weighting

    McKenna, S. J. / Nait-Charif, H. | British Library Online Contents | 2007