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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Detecting Traffic Lights by Single Shot Detection


    Contributors:


    Publication date :

    2018-11-01


    Size :

    3101209 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    DEVICE FOR DETECTING TRAFFIC LIGHTS AND METHOD OF DETECTING TRAFFIC LIGHTS

    OKI TAKAHIKO / NISHIUCHI HIDEKAZU | European Patent Office | 2017

    Free access

    METHOD AND SYSTEM FOR DETECTING TRAFFIC LIGHTS

    ZHANG YANKUN / HONG CHUYANG / JIANG RUYI et al. | European Patent Office | 2016

    Free access

    SYSTEMS AND METHODS FOR DETECTING TRAFFIC LIGHTS

    BEN SHALOM ITAI | European Patent Office | 2015

    Free access

    Method and system for detecting traffic lights

    ZHANG YANKUN / HONG CHUYANG / JIANG RUYI et al. | European Patent Office | 2015

    Free access

    Detecting and Responding to Malfunctioning Traffic Lights

    SILVER DAVID / KERSHAW CARL / HSIAO JONATHAN et al. | European Patent Office | 2024

    Free access