This paper presents an experimental study on 3D person localization (i.e. pedestrians, cyclists) in traffic scenes, using monocular vision and LiDAR data. We first analyze the detection performance of two top-ranking methods (PointPillars and AVOD) on the KITTI benchmark, with respect to varying Intersection over Union (IoU) settings and the underlying parameters of 3D bounding box location, extent and orientation. Given that the KITTI dataset contains relatively few 3D person instances, we also consider the new EuroCity Persons 2.5D (ECP2.5D) dataset, which is one order of magnitude larger. We perform domain transfer experiments between the KITTI and ECP2.5D datasets, to examine how these datasets generalize with respect to each other.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    An Experimental Study on 3D Person Localization in Traffic Scenes


    Beteiligte:


    Erscheinungsdatum :

    2020-10-19


    Format / Umfang :

    1728572 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    AN EXPERIMENTAL STUDY ON 3D PERSON LOCALIZATION IN TRAFFIC SCENES

    Van Der Sluis, Joram R. / Pool, Ewoud A. I. / Gavrila, Dariu M. | British Library Conference Proceedings | 2020


    ECP2.5D - PERSON LOCALIZATION IN TRAFFIC SCENES

    Braun, Markus / Krebs, Sebastian / Gavrila, Dariu M. | British Library Conference Proceedings | 2020


    ECP2.5D - Person Localization in Traffic Scenes

    Braun, Markus / Krebs, Sebastian / Gavrila, Dariu M. | IEEE | 2020


    Study on Detection and Localization Algorithm of Traffic Signs from Natural Scenes

    Han, Xian-Zhong / Chen, Chen / Wang, Ke-Jian et al. | Tema Archiv | 2014


    Monitoring crowded traffic scenes

    Maurin, B. / Masoud, O. / Papanikolopoulos, N. | IEEE | 2002