Learned pointcloud representations do not generalize well with an increase in distance to the sensor. For example, at a range greater than 60 meters, the sparsity of lidar pointclouds reaches a point where even humans cannot discern object shapes from each other. However, this distance should not be considered very far for fast-moving vehicles: a vehicle can traverse 60 meters in under two seconds while moving at 70 mph. For safe and robust driving automation, acute 3D object detection at these ranges is indispensable. Against this backdrop, we introduce faraway-frustum: a novel fusion strategy for detecting faraway objects. The main strategy is to depend solely on the 2D vision sensor for recognizing and classifying an object, as object shape does not change drastically with an increase in depth, and use pointcloud data for object localization in the 3D space for faraway objects. For closer objects, we use learned pointcloud representations instead, following state-of-the-art practices. This strategy alleviates the main shortcoming of object detection with learned pointcloud representations. Experiments on the KITTI dataset demonstrate that our method outperforms state-of-the-art methods by a considerable margin for faraway object detection in bird's-eye view and 3D. Our code is open-source and publicly available: https://github.com/dongfang-steven-yang/faraway-frustum.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Faraway-Frustum: Dealing with Lidar Sparsity for 3D Object Detection using Fusion


    Contributors:


    Publication date :

    2021-09-19


    Size :

    3070509 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    TEMP-FRUSTUM NET: 3D OBJECT DETECTION WITH TEMPORAL FUSION

    Erçelik, Emeç / Yurtsever, Ekim / Knoll, Alois | British Library Conference Proceedings | 2021


    Temp-Frustum Net: 3D Object Detection with Temporal Fusion

    Ercelik, Emec / Yurtsever, Ekim / Knoll, Alois | IEEE | 2021


    High Dimensional Frustum PointNet for 3D Object Detection from Camera, LiDAR, and Radar

    Wang, Leichen / Chen, Tianbai / Anklam, Carsten et al. | IEEE | 2020


    HIGH DIMENSIONAL FRUSTUM POINTNET FOR 3D OBJECT DETECTION FROM CAMERA, LIDAR, AND RADAR

    Wang, Leichen / Chen, Tianbai / Anklam, Carsten et al. | British Library Conference Proceedings | 2020


    Frustum FusionNet: Amodal 3D Object Detection with Multi-Modal Feature Fusion

    Zuo, Liangyu / Li, Yaochen / Han, Mengtao et al. | IEEE | 2021