Accurate and robust vehicle self-localization in the urban environment is a new challenge arising in the autonomous driving. GNSS positioning technique suffers from the effects of multipath and Non-Line-Of-Sight (NLOS) propagation in urban canyon. This paper proposes to employ an innovative GNSS positioning technique with the aid of 3D building map, to mitigate the error caused by multipath and NLOS. In addition, the road markings on road surface provide the significant visual information for driving, which can also be used for localization. Based on the lane marking detection, the lane keeping and changing behavior can be recognized and used for positioning. This paper integrates 3D-map-GNSS with vision-based road marking detection and 2D Map to reduce the vehicle positioning error. The experiment results demonstrate that the proposed method can provide sub-meter accuracy with respect to positioning error mean.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Correction of vehicle positioning error using 3D-map- GNSS and vision-based road marking detection


    Contributors:
    Gu, Yanlei (author) / Hsu, Li-Ta (author) / Kamijo, Shunsuke (author)


    Publication date :

    2015-11-01


    Size :

    1383207 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Road marking detection

    SPEIGLE JON / HERMAN DAVID MICHAEL / SORENSEN KYLE B | European Patent Office | 2022

    Free access

    ROAD MARKING DETECTION

    ROJAS QUINONES MARIO / HUBER MARC / TRUSOV VIKTOR | European Patent Office | 2024

    Free access

    ROAD SURFACE MARKING DETECTION DEVICE AND ROAD SURFACE MARKING DETECTION METHOD

    TANAKA SHINYA | European Patent Office | 2017

    Free access

    Cooperative GNSS Positioning aided by Road-Features Measurements

    Conde Bento, Luís | Online Contents | 2017