Lane detection plays an essential part in advanced driver-assistance systems and autonomous driving systems. However, lane detection is affected by many factors such as some challenging traffic situations. Multilane detection is also very important. To solve these problems, we proposed a lane detection method based on instance segmentation, named RS-Lane. This method is based on LaneNet and uses Split Attention proposed by ResNeSt to improve the feature representation on slender and sparse annotations like lane markings. We also use Self-Attention Distillation to enhance the feature representation capabilities of the network without adding inference time. RS-Lane can detect lanes without number limits. The tests on TuSimple and CULane datasets show that RS-Lane has achieved comparable results with SOTA and has improved in challenging traffic situations such as no line, dazzle light, and shadow. This research provides a reference for the application of lane detection in autonomous driving and advanced driver-assistance systems.


    Access

    Download


    Export, share and cite



    Title :

    RS-Lane: A Robust Lane Detection Method Based on ResNeSt and Self-Attention Distillation for Challenging Traffic Situations


    Contributors:
    Ronghui Zhang (author) / Yueying Wu (author) / Wanting Gou (author) / Junzhou Chen (author)


    Publication date :

    2021




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Robust Lane Detection via Expanded Self Attention

    Lee, Minhyeok / Lee, Junhyeop / Lee, Dogyoon et al. | ArXiv | 2021

    Free access




    Robust Lane Detection and Tracking in Challenging Scenarios

    Kim, Z. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2008