Today, deep learning detectors for autonomous driving are delivering impressive results on public datasets and in real-world applications. However, these detectors require large amounts of data, especially labeled data, to achieve the performance needed to ensure safe driving. The process of collecting and tagging data is expensive and cumbersome. Therefore, the recent focus of the industry has been on how to achieve similar performance while limiting the amount of labeled data required to train such models. Within the cross-modal active learning paradigm, we propose and analyze new strategies to exploit the inconsistencies between camera and LiDAR detectors to improve sampling efficiency and label only the samples that promise improvements for model training. For this, we leverage the 2D projection of the bounding boxes to equalize the output quality of camera and LiDAR detections. Finally, we achieve up to 0.6% AP improvement for camera and 2% improvement for LiDAR over random sampling on the KITTI dataset using a sampling strategy based on the number of detected objects.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Camera-LiDAR Inconsistency Analysis for Active Learning in Object Detection


    Beteiligte:


    Erscheinungsdatum :

    02.06.2024


    Format / Umfang :

    1814319 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Deep Learning-based Radar, Camera, and Lidar Fusion for Object Detection

    Nobis, Felix Otto Geronimo | TIBKAT | 2022

    Freier Zugriff


    /LiDAR AUTOMATED OBJECT ANNOTATION USING FUSED CAMERA/LiDAR DATA POINTS

    LIU ZHONGTAO / ESPER JAMES / LEE JONG HO | Europäisches Patentamt | 2025

    Freier Zugriff

    /LiDAR AUTOMATED OBJECT ANNOTATION USING FUSED CAMERA/LiDAR DATA POINTS

    LIU ZHONGTAO / ESPER JAMES / LEE JONG HO | Europäisches Patentamt | 2023

    Freier Zugriff

    IPCC algorithm: Moving object detection in 3D-Lidar and camera data

    Deymier, Clement / Chateau, Thierry | IEEE | 2013