Object detection in autonomous driving applications implies the detection and tracking of semantic objects that are commonly native to urban driving environments, as pedestrians and vehicles. One of the major challenges in state-of-the-art deep-learning based object detection are false positives which occur with overconfident scores. This is highly undesirable in autonomous driving and other critical robotic-perception domains because of safety concerns. This paper proposes an approach to alleviate the problem of overconfident predictions by introducing a novel probabilistic layer to deep object detection networks in testing. The suggested approach avoids the traditional Sigmoid or Softmax prediction layer which often produces overconfident predictions. It is demonstrated that the proposed technique reduces overconfidence in the false positives without degrading the performance on the true positives. The approach is validated on the 2D-KITTI objection detection through the YOLOV4 and SECOND (Lidar-based detector). The proposed approach enables interpretable probabilistic predictions without the requirement of re-training the network and therefore is very practical.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Probabilistic Approach for Road-Users Detection


    Beteiligte:
    Melotti, Gledson (Autor:in) / Lu, Weihao (Autor:in) / Conde, Pedro (Autor:in) / Zhao, Dezong (Autor:in) / Asvadi, Alireza (Autor:in) / Goncalves, Nuno (Autor:in) / Premebida, Cristiano (Autor:in)


    Erscheinungsdatum :

    2023-09-01


    Format / Umfang :

    7009762 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Pose and Semantic Map Based Probabilistic Forecast of Vulnerable Road Users’ Trajectories

    Kress, Viktor / Jeske, Fabian / Zernetsch, Stefan et al. | IEEE | 2023


    ROAD USERS AND ROAD DESIGN

    Rothengatter, J. A. / Transport Research Laboratory | British Library Conference Proceedings | 1999


    Vulnerable Road Users Detection Using V2X Communications

    Anaya, Jose J. / Talavera, Edgar / Gimenez, David et al. | IEEE | 2015


    Understanding road users’ expectations

    M. Houtenbos / H. M. Jagtman / M. P. Hagenzieker et al. | DOAJ | 2005

    Freier Zugriff

    Vulnerable Road Users: Cyclist

    Slop, M. / Vag-och transport-forskningsinstitutet | British Library Conference Proceedings | 1992