To achieve fully autonomous navigation, vehicles need to compute an accurate model of their direct surrounding. In this paper, a 3D surface reconstruction algorithm from heterogeneous density 3D data is presented. The proposed method is based on a TSDF voxel-based representation, where an adaptive neighborhood kernel sourced on a Gaussian confidence evaluation is introduced. This enables to keep a good trade-off between the density of the reconstructed mesh and its accuracy. Experimental evaluations carried on both synthetic (CARLA) and real (KITTI) 3D data show a good performance compared to a state of the art method used for surface reconstruction.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    3D Surface Reconstruction from Voxel-based Lidar Data


    Beteiligte:


    Erscheinungsdatum :

    01.10.2019


    Format / Umfang :

    3050986 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Characterizing Perspective Error in Voxel-Based Lidar Scan Matching

    Jason H. Rife / Matthew McDermott | DOAJ | 2024

    Freier Zugriff

    Photorealistic Scene Reconstruction by Voxel Coloring

    Seitz, S. M. / Dyer, C. R. | British Library Online Contents | 1999


    A Voxel-Based Method for Automated Detection and Mapping of Light Poles on Rural Highways using LiDAR Data

    Gargoum, Suliman A. / Koch, James C. / El-Basyouny, Karim | Transportation Research Record | 2018


    MR3D-Net: Dynamic Multi-Resolution 3D Sparse Voxel Grid Fusion for LiDAR-Based Collective Perception

    Teufel, Sven / Gamerdinger, Jorg / Volk, Georg et al. | IEEE | 2024


    Offline Reconstruction of Missing Vehicle Trajectory Data from 3D LIDAR

    Sazara, Cem / Vatani Nezafat, Reza / Cetin, Mecit | British Library Conference Proceedings | 2017