Motion is an important clue for many tasks in visual scene perception. In this paper, we present a new matching-based algorithm to estimate nearly dense optical flow fields for the static parts of the scene, i.e. those parts whose motion is induced by the moving observer only. Our algorithm is designed for applications in intelligent vehicles usually equipped with stereo camera rigs. To address the computational effort of matching-based approaches we use constraints arising from the geometry between multiple views. To this end, we compute both an approximated optical flow field and an approximated disparity field between left and right image. Hence, we can predict the position of the corresponding candidate and limit the search space to a small neighborhood around the predicted position leading to near real-time capabilities. Experiments on different challenging real world images show the accuracy and efficiency of the proposed approach.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Trinocular optical flow estimation for intelligent vehicle applications


    Beteiligte:
    Kitt, Bernd (Autor:in) / Lategahn, Henning (Autor:in)


    Erscheinungsdatum :

    01.09.2012


    Format / Umfang :

    558841 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Trinocular Geometry Revisited

    Trager, M. / Ponce, J. / Hebert, M. | British Library Online Contents | 2016


    A highly parallel trinocular stereo algorithmus

    Ferrari,D. / Garibotto,G. / Pardo,A. et al. | Kraftfahrwesen | 1988


    3 Eyes: A Trinocular Active Vision System

    Cumani, A. / Guiducci, A. / Grattoni, P. et al. | British Library Conference Proceedings | 1994


    Trinocular ground system to control UAVs

    Martinez, Carol / Campoy, Pascual / Mondragon, Ivan et al. | Tema Archiv | 2009


    Trinocular Vision Systems For Unmanned Aerial Vehicles

    ROBBINS-ROTHMAN ASHER MENDEL / O'ROURKE KELLEN JAMES WATERMAN / LEBOVITZ ADAM NATHAN et al. | Europäisches Patentamt | 2025

    Freier Zugriff