Detecting the road geometry at night time is an essential precondition to provide optimal illumination for the driver and the other traffic participants. In this paper we propose a novel approach to estimate the current road curvature based on three sensors: A far infrared camera, a near infrared camera and an imaging radar sensor. Various Convolutional Neural Networks with different configuration are trained for each input. By fusing the classifier responses of all three sensors, a further performance gain is achieved. To annotate the training and evaluation dataset without costly human interaction a fully automatic curvature annotation algorithm based on inertial navigation system is presented as well.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Night time road curvature estimation based on Convolutional Neural Networks


    Beteiligte:
    Hartmann, Oliver (Autor:in) / Schweiger, Roland (Autor:in) / Wagner, Raimar (Autor:in) / Schule, Florian (Autor:in) / Gabb, Michael (Autor:in) / Dietmayer, Klaus (Autor:in)


    Erscheinungsdatum :

    01.06.2013


    Format / Umfang :

    787296 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    NIGHT TIME ROAD CURVATURE ESTIMATION BASED ON CONVOLUTIONAL NEURAL NETWORKS

    Hartmann, O. / Schweiger, R. / Wagner, R. et al. | British Library Conference Proceedings | 2013


    Convolutional Neural Networks for night-time animal orientation estimation

    Wagner, Raimar / Thom, Markus / Gabb, Michael et al. | IEEE | 2013


    CONVOLUTIONAL NEURAL NETWORKS FOR NIGHT-TIME ANIMAL ORIENTATION ESTIMATION

    Wagner, R. / Thom, M. / Gabb, M. et al. | British Library Conference Proceedings | 2013


    ROAD CURVATURE ESTIMATION DEVICE

    HIRATA ATSUHIRO / MUNAKATA ATSUKI | Europäisches Patentamt | 2024

    Freier Zugriff

    Road curvature estimation device

    HIRATA ATSUHIRO / MUNEKATA ATSUKI | Europäisches Patentamt | 2024

    Freier Zugriff