This paper presents a novel focus-of-attention strategy for monocular pedestrian recognition. It uses Bayes’ rule to estimate the posterior for the presence of a pedestrian in a certain (rectangular) image region, based on motion parallax features. This posterior is used as a parameter to control the amount of regions of interest (ROIs) that is passed to subsequent verification stages. For the latter, we use a state-of-the-art pedestrian recognition scheme which consists of multiple modules in a cascade architecture. We obtain optimized settings for the control parameters of the combined cascade system by a sequential ROC convex hull technique. Experiments are conducted on image data captured from a moving vehicle in an urban environment. We demonstrate that the proposed focus-of-attention strategy reduces the false positives of an otherwise identical monocular pedestrian recognition system by a factor of two, at equal detection rates. The overall system maintains processing rates close to real-time.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Monocular pedestrian recognition using motion parallax


    Beteiligte:
    Enzweiler, M. (Autor:in) / Kanter, P. (Autor:in) / Gavrila, D. M. (Autor:in)


    Erscheinungsdatum :

    01.06.2008


    Format / Umfang :

    1517061 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Monocular Pedestrian Recognition Using Motion Parallax

    Enzweiler, M. / Kanter, P. / Gavrila, D.M. | British Library Conference Proceedings | 2008



    Pedestrian candidates generation using monocular cues

    Cheda, Diego / Ponsa, Daniel / Lopez, Antonio M. | IEEE | 2012


    Pedestrian Candidates Generation Using Monocular Cues

    Cheda, D. / Ponsa, D. / Lopez, A.M. et al. | British Library Conference Proceedings | 2012