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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

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


    Contributors:
    Feng, Di (author) / Cao, Yifan (author) / Rosenbaum, Lars (author) / Timm, Fabian (author) / Dietmayer, Klaus (author)


    Publication date :

    2020-10-19


    Size :

    1296280 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




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

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



    Leveraging Thermal Imaging for Autonomous Driving

    Miethig, Ben / Liu, Ash / Habibi, Saeid et al. | IEEE | 2019


    Deep Learning-Based Multi-scale Multi-object Detection and Classification for Autonomous Driving

    Fink, Maximilian / Liu, Ying / Engstle, Armin et al. | Springer Verlag | 2019