LiDARs are usually more accurate than cameras in distance measuring. Hence, there is strong interest to apply LiDARs in autonomous driving. Different existing approaches process the rich 3D point clouds for object detection, tracking and recognition. These methods generally require two initial steps: (1) filter points on the ground plane and (2) cluster non-ground points into objects. This paper proposes a field-tested fast 3D point cloud segmentation method for these two steps. Our specially designed algorithms allow instantly process raw LiDAR data packets, which significantly reduce the processing delay. In our tests on Velodyne UltraPuck, a 32 layers spinning LiDAR, the processing delay of clustering all the 360° LiDAR measures is less than 1ms. Meanwhile, a coarse-to-fine scheme is applied to ensure the clustering quality. Our field experiments in public roads have shown that the proposed method significantly improves the speed of 3D point cloud clustering whilst maintains good accuracy.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    InsClustering: Instantly Clustering LiDAR Range Measures for Autonomous Vehicle


    Beteiligte:
    Li, You (Autor:in) / Bihan, Clement Le (Autor:in) / Pourtau, Txomin (Autor:in) / Ristorcelli, Thomas (Autor:in)


    Erscheinungsdatum :

    20.09.2020


    Format / Umfang :

    1756651 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Autonomous vehicle LIDAR mirror

    HUEBNER ANNETTE LYNN / DELLOCK PAUL KENNETH / SALTER STUART C et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    AUTONOMOUS VEHICLE LIDAR MIRROR

    HUEBNER ANNETTE LYNN / DELLOCK PAUL KENNETH / SALTER STUART C et al. | Europäisches Patentamt | 2018

    Freier Zugriff


    LIDAR BASE, LIDAR DEVICE AND AUTONOMOUS VEHICLE

    REN RUI / FAN ZONGTAO / WANG BOLEI et al. | Europäisches Patentamt | 2023

    Freier Zugriff