Monocular road segmentation is a fundamental component of autonomous driving. High accuracy has always been a focus of the community for this task. However, the exploration of high-speed methods is still lacking. This limits the prevalence of the monocular road segmentation method. In this paper, an efficient encoder-decoder network is proposed for segmenting the road from a single image. Specifically, to achieve high-speed inference, we leverage a shallow encoder for feature extraction and design a lightweight decoder for feature resolution recovery. To avoid the accuracy drop caused by network simplification, we introduce an efficient asymmetric dilated block to improve the ability of features to distinguish drivable/nondrivable roads to maintain the performance without excess computation. Experiments on three datasets verify the effectiveness of our method. On KITTI-Road, our approach ranks second among all monocular methods and even achieves a competitive performance compared to multimodal methods, with an inference speed over 135 FPS on a single TITAN Xp, which is at least 20 times faster than the state-of-the-art monocular method. Furthermore, our approach can be deployed on the embedded platform Jetson TX2 and achieves a speed of over 80 FPS. Codes will be available at https://github.com/gongshichina/FastRoadSeg.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    FastRoadSeg: Fast Monocular Road Segmentation Network


    Contributors:
    Gong, Shi (author) / Zhou, Huan (author) / Xue, Feng (author) / Fang, Cong (author) / Li, Yiqun (author) / Zhou, Yu (author)

    Published in:

    Publication date :

    2022-11-01


    Size :

    3876639 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Monocular Road Segmentation Using Slow Feature Analysis

    Kuhnl, T. / Kummert, F. / Fritsch, J. et al. | British Library Conference Proceedings | 2011


    WarpCut - fast obstacle segmentation in monocular video

    Wedel, Andreas / Schoenemann, Thomas / Brox, Thomas et al. | Tema Archive | 2007


    Monocular motion segmentation

    Romera,M.M. / Pagel,F. / Fraunhofer Inst.f.Informations.u.Datenverarbeitung,IITB,DE | Automotive engineering | 2009


    Quadtree Segmentation Network for Obstacle Avoidance in Monocular Navigation

    Braun, Daniel / Morel, Olivier / Vasseur, Pascal et al. | IEEE | 2022