Understanding the surrounding environment of the vehicle is still one of the challenges for autonomous driving. This paper addresses 360-degree road scene semantic segmentation using surround view cameras, which are widely equipped in existing production cars. First, in order to address large distortion problem in the fisheye images, Restricted Deformable Convolution (RDC) is proposed for semantic segmentation, which can effectively model geometric transformations by learning the shapes of convolutional filters conditioned on the input feature map. Second, in order to obtain a large-scale training set of surround view images, a novel method called zoom augmentation is proposed to transform conventional images to fisheye images. Finally, an RDC based semantic segmentation model is built; the model is trained for real-world surround view images through a multi-task learning architecture by combining real-world images with transformed images. Experiments demonstrate the effectiveness of the RDC to handle images with large distortions, and that the proposed approach shows a good performance using surround view cameras with the help of the transformed images.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Restricted Deformable Convolution-Based Road Scene Semantic Segmentation Using Surround View Cameras


    Contributors:
    Deng, Liuyuan (author) / Yang, Ming (author) / Li, Hao (author) / Li, Tianyi (author) / Hu, Bing (author) / Wang, Chunxiang (author)


    Publication date :

    2020-10-01


    Size :

    4722573 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Structured Bird’s-Eye View Road Scene Understanding from Surround Video

    Jia, Peng / Gong, Jianwei / Jiang, Yahui et al. | IEEE | 2024


    SoilingNet: Soiling Detection on Automotive Surround-View Cameras

    Uricar, Michal / Krizek, Pavel / Sistu, Ganesh et al. | IEEE | 2019


    Machine Learning-based Stereo Vision Algorithm for Surround View Fisheye Cameras

    Akita, Tokihiko / Yamauchi, Yuji / Fujiyoshi, Hironobu | IEEE | 2018


    METHOD FOR GENERATING SURROUND VIEW IMAGES DERIVED FROM IMAGE DATA CAPTURED BY CAMERAS OF A VEHICULAR SURROUND VIEW VISION SYSTEM

    IHLENBURG JOERN / PFLUG GOERG / GIESEKE ACHIM | European Patent Office | 2021

    Free access