In this paper we present CMRNet, a realtime approach based on a Convolutional Neural Network (CNN) to localize an RGB image of a scene in a map built from LiDAR data. Our network is not trained in the working area, i. e., CMRNet does not learn the map. Instead it learns to match an image to the map. We validate our approach on the KITTI dataset, processing each frame independently without any tracking procedure. CMRNet achieves 0.27m and 1.07° median localization accuracy on the sequence 00 of the odometry dataset, starting from a rough pose estimate displaced up to 3.5m and 17°. To the best of our knowledge this is the first CNN-based approach that learns to match images from a monocular camera to a given, preexisting 3D LiDAR-map.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    CMRNet: Camera to LiDAR-Map Registration


    Contributors:
    Cattaneo, D. (author) / Vaghi, M. (author) / Ballardini, A. L. (author) / Fontana, S. (author) / Sorrenti, D. G. (author) / Burgard, W. (author)


    Publication date :

    2019-10-01


    Size :

    3017103 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    MOTION MONITOR USING LIDAR REGISTRATION

    LONGMAN OREN / ZAC NOAM / FURMAN TAL | European Patent Office | 2023

    Free access

    LIDAR-Camera Fusion Where LIDAR and Camera Validly See Different Things

    BLAU CHAIM / SPRINGER OFER / ROSENBLUM KEVIN et al. | European Patent Office | 2022

    Free access

    LiDAR MERGING LiDAR INFORMATION AND CAMERA INFORMATION

    LEE JONG HO | European Patent Office | 2022

    Free access

    LiDAR MERGING LiDAR INFORMATION AND CAMERA INFORMATION

    LEE JONG HO | European Patent Office | 2022

    Free access