Localization and perception research for Autonomous Driving is mainly focused on camera and LiDAR data, rarely on radar data. We apply an automated labeling pipeline to semantically annotate real world radar measurements, manually correct point-wise labels to obtain ground-truth, and apply supervised learning models on this data. To assign an attribute, called class label, to every point of an input cloud is hereby referred to as semantic segmentation. Transferring approaches of LiDAR segmentation into the similar data structure, we research deep-learning semantic segmentation on radar point clouds. Compared to classical Cartesian coordinates, a polar coordinate input discretization benefits the dynamically changing number of radar detections per sensing cycle and simplifies to model the quasi-radial sensor resolution. Moreover, we evaluate different network architectures, examine radar feature channels and also temporal consistency by attention map concatenation. Our contribution is twofold. First, featuring a semantically labeled real world radar dataset for ground truth. Second, our supervised learning approach to solve semantic segmentation on radar point-cloud data. Our classification benchmark network yields 56.1 % weighted Intersection of a Union of relevant classes for radar, while reaching a real-time framerate of 12.4ms.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning Semantics on Radar Point-Clouds


    Beteiligte:


    Erscheinungsdatum :

    2021-07-11


    Format / Umfang :

    2203644 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    GENERATING POINT CLOUDS BASED UPON RADAR TENSORS

    KUSCHK GEORG / CANALS MARC UNZUETA / MÖLLER SVEN et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    SERALOC: SLAM on semantically annotated radar point-clouds

    Isele, Simon T. / Haas-Fickinger, Fabian / Zollner, J. Marius | IEEE | 2021


    Simulation of automotive radar point clouds in standardized frameworks

    Eder, Thomas / Technische Universität München / Eric Cuvillier, Firma | GWLB - Gottfried Wilhelm Leibniz Bibliothek | 2021


    Simulation of automotive radar point clouds in standardized frameworks

    Eder, Thomas / Technische Universität München / Eric Cuvillier, Firma | TIBKAT | 2021


    4D High-Resolution Imagery of Point Clouds for Automotive mmWave Radar

    Jiang, Mengjie / Xu, Gang / Pei, Hao et al. | IEEE | 2024