Vision-based lane detection methods often rely on lane markings in image streams as the only source of information to determine lane boundaries. However, different road conditions such as strong shadows and lighting changes present significant challenges in extracting lane marking features, which may result in inaccurate or inconsistent lane boundary detections. This paper proposes GPS-Guided Lane Detection (GPS-LD) as a robust lane detection method that uses conventional image processing techniques for feature extraction and global route data as prior information to determine lane boundaries. The proposed method uses the route from the mission planner to determine the shape of the road in front of the vehicle. The road shape extracted from the route data is then used as a reference to cluster lane marking features and to verify the lane boundary detection results. The proposed method is evaluated on the KITTI dataset and the detection performance is comparable to state-of-the-art lane detection methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    GPS-guided Vision-based Lane Detection for Autonomous Vehicles


    Beteiligte:


    Erscheinungsdatum :

    24.09.2023


    Format / Umfang :

    3648222 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Lane estimation for autonomous vehicles using vision and LIDAR

    Huang, Albert Shuyu | DSpace@MIT | 2010

    Freier Zugriff

    Recent Advances in Computer Vision Technologies for Lane Detection in Autonomous Vehicles

    Anto, Harshitha Devina / Malathi, G. / Kumar, G. Bharadwaja et al. | Springer Verlag | 2023


    The Autonomous Lane-Change of the Vision-based Intelligent Micro-vehicles

    Bi, J. / Wang, J. / Jiang, Y. | British Library Online Contents | 2013


    REDUNDANT LANE DETECTION FOR AUTONOMOUS VEHICLES

    STAMENKOVICH JOSEPH | Europäisches Patentamt | 2025

    Freier Zugriff