We present and evaluate a novel scene descriptor for classifying urban traffic by object motion. Atomic 3D flow vectors are extracted and compensated for the vehicle's egomotion, using stereo video sequences. Votes cast by each flow vector are accumulated in a bird's eye view histogram grid. Since we are directly using low-level object flow, no prior object detection or tracking is needed. We demonstrate the effectiveness of the proposed descriptor by comparing it to two simpler baselines on the task of classifying more than 100 challenging video sequences into intersection and non-intersection scenarios. Our experiments reveal good classification performance in busy traffic situations, making our method a valuable complement to traditional approaches based on lane markings.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Object flow: A descriptor for classifying traffic motion


    Beteiligte:
    Geiger, Andreas (Autor:in) / Kitt, Bernd (Autor:in)


    Erscheinungsdatum :

    01.06.2010


    Format / Umfang :

    1249181 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    ObjectFlow: A Descriptor for Classifying Traffic Motion, pp. 287-293

    Geiger, A. / Kitt, B. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2010


    Classifying web videos using a global video descriptor

    Solmaz, B. / Assari, S. M. / Shah, M. | British Library Online Contents | 2013


    Method And System For Classifying Traffic Flow

    CORNTHWAITE DON / RAJU DANIEL / PEACOCK TROY et al. | Europäisches Patentamt | 2017

    Freier Zugriff

    Method and system for classifying traffic flow

    CORNTHWAITE DON / RAJU DANIEL / PEACOCK TROY et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    METHOD AND SYSTEM FOR CLASSIFYING TRAFFIC FLOW

    CORNTHWAITE DON / RAJU DANIEL / PEACOCK TROY et al. | Europäisches Patentamt | 2015

    Freier Zugriff