This work presents a probabilistic deep neural network that combines LiDAR point clouds and RGB camera images for robust, accurate 3D object detection. We explicitly model uncertainties in the classification and regression tasks, and leverage uncertainties to train the fusion network via a sampling mechanism. We validate our method on three datasets with challenging real-world driving scenarios. Experimental results show that the predicted uncertainties reflect complex environmental uncertainty like difficulties of a human expert to label objects. The results also show that our method consistently improves the Average Precision by up to 7% compared to the baseline method. When sensors are temporally misaligned, the sampling method improves the Average Precision by up to 20%, showing its high robustness against noisy sensor inputs.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Leveraging Uncertainties for Deep Multi-modal Object Detection in Autonomous Driving


    Beteiligte:
    Feng, Di (Autor:in) / Cao, Yifan (Autor:in) / Rosenbaum, Lars (Autor:in) / Timm, Fabian (Autor:in) / Dietmayer, Klaus (Autor:in)


    Erscheinungsdatum :

    19.10.2020


    Format / Umfang :

    1296280 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    LEVERAGING UNCERTAINTIES FOR DEEP MULTI-MODAL OBJECT DETECTION IN AUTONOMOUS DRIVING

    Feng, Di / Cao, Yifan / Rosenbaum, Lars et al. | British Library Conference Proceedings | 2020




    Multi-Modal 3D Object Detection in Autonomous Driving: A Survey and Taxonomy

    Wang, Li / Zhang, Xinyu / Song, Ziying et al. | IEEE | 2023


    MENet: Multi-Modal Mapping Enhancement Network for 3D Object Detection in Autonomous Driving

    Liu, Moyun / Chen, Youping / Xie, Jingming et al. | IEEE | 2024