Recent improvements in object detection are driven by the success of convolutional neural networks (CNN). They are able to learn rich features outperforming hand-crafted features. So far, research in traffic light detection mainly focused on hand-crafted features, such as color, shape or brightness of the traffic light bulb. This paper presents a deep learning approach for accurate traffic light detection in adapting a single shot detection (SSD) approach. SSD performs object proposals creation and classification using a single CNN. The original SSD struggles in detecting very small objects, which is essential for traffic light detection. By our adaptations it is possible to detect objects much smaller than ten pixels without increasing the input image size. We present an extensive evaluation on the DriveU Traffic Light Dataset (DTLD). We reach both, high accuracy and low false positive rates. The trained model is real-time capable with ten frames per second on a Nvidia Titan Xp. Code has been made available at https://github.com/julimueller/tl_ssd.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Detecting Traffic Lights by Single Shot Detection


    Beteiligte:
    Muller, Julian (Autor:in) / Dietmayer, Klaus (Autor:in)


    Erscheinungsdatum :

    01.11.2018


    Format / Umfang :

    3101209 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    DEVICE FOR DETECTING TRAFFIC LIGHTS AND METHOD OF DETECTING TRAFFIC LIGHTS

    OKI TAKAHIKO / NISHIUCHI HIDEKAZU | Europäisches Patentamt | 2017

    Freier Zugriff

    METHOD AND SYSTEM FOR DETECTING TRAFFIC LIGHTS

    ZHANG YANKUN / HONG CHUYANG / JIANG RUYI et al. | Europäisches Patentamt | 2016

    Freier Zugriff

    SYSTEMS AND METHODS FOR DETECTING TRAFFIC LIGHTS

    BEN SHALOM ITAI | Europäisches Patentamt | 2015

    Freier Zugriff

    Method and system for detecting traffic lights

    ZHANG YANKUN / HONG CHUYANG / JIANG RUYI et al. | Europäisches Patentamt | 2015

    Freier Zugriff

    Detecting and Responding to Malfunctioning Traffic Lights

    SILVER DAVID / KERSHAW CARL / HSIAO JONATHAN et al. | Europäisches Patentamt | 2024

    Freier Zugriff