In this work, we outline a process for traffic light detection in the context of autonomous vehicles and driver assistance technology features. For our approach, we leverage the automatic annotations from virtually generated data of road scenes. Using the automatically generated bounding boxes around the illuminated traffic lights themselves, we trained an 8-layer deep neural network, without pre-training, for classification of traffic light signals (green, amber, red). After training on virtual data, we tested the network on real world data collected from a forward facing camera on a vehicle. Our new region proposal technique uses color space conversion and contour extraction to identify candidate regions to feed to the deep neural network classifier. Depending on time of day, we convert our RGB images in order to more accurately extract the appropriate regions of interest and filter them based on color, shape and size. These candidate regions are fed to a deep neural network. In this paper, we focus on a region of interest (ROI) proposal method, which works to minimize false negative and false positive candidate regions that are then fed to the deep neural network for classification. This camera-only solution has applications for many levels of autonomy, from driver assistance technology (SAE Level 2) to fully automated vehicles (SAE Level 4).


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Region Proposal Technique for Traffic Light Detection Supplemented by Deep Learning and Virtual Data


    Additional title:

    Sae Technical Papers


    Contributors:

    Conference:

    WCX™ 17: SAE World Congress Experience ; 2017



    Publication date :

    2017-03-28




    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Big Data architecture proposal for vehicular traffic detection

    Herrera Herrera, Nelson Ivan | IEEE | 2020


    Traffic Light Cycle Control using Deep Reinforcement Technique

    Sahu, Satya Prakash / Dewangan, Deepak Kr. / Agrawal, Archit et al. | IEEE | 2021


    Deep reinforcement learning traffic light control method

    KONG YAN / LI YING / CHIH-CHAO YANG | European Patent Office | 2024

    Free access

    Traffic light detection and classification using computer vision and deep learning

    MARYAM MOOSAEI / MADELINE J GOH / VIDYA NARIYAMBUT MURALI et al. | European Patent Office | 2018

    Free access

    Road surface traffic sign detection with hybrid region proposal and fast R-CNN

    Qian, Rongqiang / Liu, Qianyu / Yue, Yong et al. | IEEE | 2016