Monocular 3D object detection is an ill-posed problem due to the loss of geometry information in 2D images. To improve the reliability of monocular vision system, we propose to replace the deterministic estimation with a probabilistic prediction by computing both aleatoric and epistemic uncertainty in 3D detection task. We further design a continuous focal loss that can improve location accuracy and when combining with aleatoric uncertainty estimation, also reduce the effect of noise data during training. Our method is capable of estimating uncertainty in a single forward pass while achieving nearly real-time performance with 0.1s per image on a modern platform. Additionally, to make fair comparison between point and probabilistic prediction, we present a novel probabilistic localization evaluation metric which computes the average error over the predicted location distribution. Our experiments indicate that we achieve competitive result on the official KITTI 3D detection leaderboard, among other deterministic methods. Furthermore, our method gains more accurate localization accuracy under different localization evaluation metrics.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Efficient Uncertainty Estimation for Monocular 3D Object Detection in Autonomous Driving


    Contributors:
    Liu, Zechen (author) / Han, Zhihua (author)


    Publication date :

    2021-09-19


    Size :

    2111128 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Federated Monocular 3D Object Detection for Autonomous Driving

    Chi, Fangyuan / Wang, Yixiao / Nasiopoulos, Panos et al. | TIBKAT | 2023

    Free access

    DIRTY MONOCULAR CAMERA DETECTION METHODS FOR AUTONOMOUS DRIVING VEHICLE

    ZHU FAN | European Patent Office | 2021

    Free access

    Dirty monocular camera detection methods for autonomous driving vehicle

    ZHU FAN | European Patent Office | 2023

    Free access

    BEV-MODNet: Monocular Camera based Bird's Eye View Moving Object Detection for Autonomous Driving

    Rashed, Hazem / Essam, Mariam / Mohamed, Maha et al. | IEEE | 2021


    Efficient Monocular Coarse-to-Fine Object Pose Estimation

    Feng, Rong / Zhang, Hong | British Library Conference Proceedings | 2016