Overhead presentation. Video technology is applied in - night vision systems for high beam visibility in low beam situations and brilliant images, - lane detection for adaptive lane departure warning, lane keeping support, - object detection and - road sign recognition. A collision protection system for day and night has high customer benefit especially in surprising situations. A new algorithm for optical flow is proposed: PowerFlow. Herein special features are extracted in one run from the image and processed, after processing features from subsequent images can easily be matched and flow hypotheses can be determined without any model assumptions, without any constraints on flow length, with a previously unknown flow density, enabling algorithmic approach for object detection and ego motion estimation. PowerFlow detects objects within a time under 160 msec even if they are partially occluded.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Pedestrian detection with monocular vision system


    Beteiligte:
    Schick, Jens (Autor:in)


    Erscheinungsdatum :

    2006


    Format / Umfang :

    8 Seiten, 13 Bilder




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch




    Pedestrian detection with monocular vision system

    Schick,J. / Bosch,Leonberg,DE | Kraftfahrwesen | 2006


    A monocular vision based pedestrian detection system for intelligent vehicles

    Liping Yu, / Wentao Yao, / Huaping Liu, et al. | IEEE | 2008


    A Monocular Vision Based Pedestrian Detection System for Intelligent Vehicles

    Yu, L. / Yao, W. / Liu, H. | British Library Conference Proceedings | 2008


    Algorithm Study for Pedestrian Detection Based on Monocular Vision

    Lie, Guo / Rong-ben, Wang / Li-sheng, Jin et al. | IEEE | 2006


    Monocular pedestrian recognition using motion parallax

    Enzweiler, M. / Kanter, P. / Gavrila, D. M. | IEEE | 2008