Lane marking detection, as a key technique for the Highly Automated Driving (HAD) Map, has drawn much attention recently. Traditional methods mainly focused on processing color images, where the performance was affected by illumination variation, over-exposure and occlusion severely. Confronted with above problems, this paper proposes a lane detection algorithm based on Convolution Neural Network (CNN) from point clouds. Our contributions are twofold. On one hand, a CNN framework via gradual up-sampling is introduced, where robust and accurate detection results are achieved. Before applying the CNN model, we also design pre-processing steps, including point clouds registration, the road surface segmentation and orthogonal projection. On the other hand, we propose to analyze the layout of lanes by utilizing the global information and domain knowledge. Hence, false detections caused by ground arrows and texts could be eliminated. Visual and quantitative experiments demonstrate the effectiveness of our algorithm.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Lane marking detection based on Convolution Neural Network from point clouds


    Beteiligte:
    Bei He, (Autor:in) / Rui Ai, (Autor:in) / Yang Yan, (Autor:in) / Xianpeng Lang, (Autor:in)


    Erscheinungsdatum :

    2016-11-01


    Format / Umfang :

    3010267 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    LANE MARKING DETECTION SYSTEM AND LANE MARKING DETECTION METHOD

    TAKEMAE KASHU | Europäisches Patentamt | 2015

    Freier Zugriff

    PCRLaneNet: Lane Marking Detection via Point Coordinate Regression

    Wang, Pan / Xue, Jianru / Dou, Jian et al. | IEEE | 2021



    LANE MARKING DETECTION SYSTEM

    OGASAWARA SHIGERU / UMEMI YUICHI / UNO AKINORI et al. | Europäisches Patentamt | 2018

    Freier Zugriff

    DETECTION OF LANE MARKING

    DONALD JASON BURNETTE / DAVID I FERGUSON | Europäisches Patentamt | 2018

    Freier Zugriff