In this paper the authors introduce a new approach to enhance the performance of pedestrian recognition using stereo vision systems. The main idea of the proposed approach is to combine the disparity computation with a grouping algorithm, which is normally carried out sequentially. Thereby the disparity determination becomes more reliable and the segmentation delivers better results compared with applying on greyscale images as well as in a sequential form of processing.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Contour following based disparity computation for pedestrian detection


    Additional title:

    Fußgängererkennung mit Hilfe der Nachbildung der Kontour basierend auf der Ungleichheitsberechnung


    Contributors:


    Publication date :

    2001


    Size :

    4 Seiten, 3 Bilder, 13 Quellen


    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English





    Enhanced disparity computation for ADAS applications

    Fardi, Basel / Abbas, Ammar / Wanielik, Gerd | Tema Archive | 2007


    Geometric Constraints and Stereo Disparity Computation

    Stewart, C. V. / Flatland, R. Y. / Bubna, K. | British Library Online Contents | 1996


    Pedestrian detection for intelligent vehicles based on active contour models and stereo vision

    Hilario, C. / Collado, J.M. / Armingol, Jose Maria et al. | Tema Archive | 2005


    A hybrid approach for stereo disparity computation

    Valentinotti, F. / Taraglio, S. | British Library Online Contents | 1999