Autonomous driving datasets are often skewed and in particular, lack training data for objects at farther distances from the ego vehicle. The imbalance of data causes a performance degradation as the distance of the detected objects increases. In this paper, we propose pattern-aware ground truth sampling, a data augmentation technique that downsamples an object's point cloud based on the LiDAR's characteristics. Specifically, we mimic the natural diverging point pattern variation that occurs for objects at depth to simulate samples at farther distances. Thus, the network has more diverse training examples and can generalize to detecting farther objects more effectively. We evaluate against existing data augmentation techniques that use point removal or perturbation methods and find that our method outperforms all of them. Additionally, we propose using equal element AP bins to evaluate the performance of 3D object detectors across distance. We improve the performance of PV-RCNN on the car class by more than 0.7 percent on the KITTI validation split at distances greater than 25 m.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Pattern-Aware Data Augmentation for LiDAR 3D Object Detection


    Contributors:


    Publication date :

    2021-09-19


    Size :

    1750197 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Evaluation of Point Cloud Data Augmentation for 3D-LiDAR Object Detection in Autonomous Driving

    Martins, Marta / Gomes, Iago P. / Wolf, Denis Fernando et al. | Springer Verlag | 2024



    LANGUAGE-BASED OBJECT DETECTION AND DATA AUGMENTATION

    SCHULTER SAMUEL / AICH ABHISHEK / GOPALKRISHNA VIJAY KUMAR BAIKAMPADY | European Patent Office | 2025

    Free access

    Spatial aware object detection by LIDAR and camera fusion based super-resolution

    KABAI ROBERT-ZSOLT | European Patent Office | 2024

    Free access

    Context-aware pedestrian detection using LIDAR

    Oliveira, L / Nunes, U | IEEE | 2010