We propose a multi-layer, real-time vehicle detection and tracking system using stereo vision, multi-view AdaBoost detectors, and optical flow. By adopting a ground plane estimate extracted from stereo information, we generate a sparse set of hypotheses and apply trained AdaBoost classifiers in addition to fast disparity histogramming, for Hypothesis Verification (HV) purposes. Our tracking system employs one Kalman filter per detected vehicle and motion vectors from optical flow, as a means to increase its robustness. An acceptable detection rate with few false positives is obtained at 25 fps with generic hardware.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Real-time vehicle detection and tracking using stereo vision and multi-view AdaBoost


    Beteiligte:
    Kowsari, T. (Autor:in) / Beauchemin, S. S. (Autor:in) / Cho, J. (Autor:in)


    Erscheinungsdatum :

    01.10.2011


    Format / Umfang :

    1106365 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Video-based, real-time multi-view stereo

    Vogiatzis, G. / Hernandez, C. | British Library Online Contents | 2011


    Stereo vision based vehicle detection

    Kormann, Benjamin / Neve, Antje / Klinker, Gudrun et al. | Tema Archiv | 2010


    Performance Improvement of Vehicle Tracking Using Parts Features Adaboost

    Do, Jingyu / Park, Jangsik / Kim, Hyuntae | Springer Verlag | 2013


    Stereo Vision-based Vehicle Detection

    Broggi, A. / Nichele, S. / Bertozzi, M. et al. | British Library Conference Proceedings | 2000


    Stereo vision-based vehicle detection

    Bertozzi, M. / Broggi, A. / Fascioli, A. et al. | IEEE | 2000