We propose a data-driven method for simulating lidar sensors. The method reads computer-generated data, and (i) extracts geometrically simulated lidar point clouds and (ii) predicts the strength of the lidar response – lidar intensities. Qualitative evaluation of the proposed pipeline demonstrates the ability to predict systematic failures such as no/low responses on polished parts of car bodyworks and windows, or strong responses on reflective surfaces such as traffic signs and license/registration plates. We also experimentally show that enhancing the training set by such simulated data improves the segmentation accuracy on the real dataset with limited access to real data. Implementation of the resulting lidar simulator for the GTA V game, as well as the accompanying large dataset, is made publicly available.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Learning to Predict Lidar Intensities


    Beteiligte:
    Vacek, Patrik (Autor:in) / Jasek, Otakar (Autor:in) / Zimmermann, Karel (Autor:in) / Svoboda, Tomas (Autor:in)


    Erscheinungsdatum :

    2022-04-01


    Format / Umfang :

    2535416 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    GRAIL: A Gradients-of-Intensities-based Local Descriptor for Map-based Localization Using LiDAR Sensors

    Hungar, Constanze / Brakemeier, Sara / Jurgens, Stefan et al. | IEEE | 2019



    Beam Splitter Intensities Are Preselected

    Campbell, W. / Owen, R. B. | NTRS | 1982


    Study of passenger transport intensities

    deMelverda, H.A.A. | Engineering Index Backfile | 1948


    Learning to predict train wheel failures

    Yang, Chunsheng / Letourneau, Sylvain | Tema Archiv | 2005