Multi-sensor object detection is an active research topic in automated driving, but the robustness of such detection models against missing sensor input (modality missing), e.g., due to a sudden sensor failure, is a critical problem which remains under-studied. In this work, we propose UniBEV, an end-to-end multi-modal 3D object detection framework designed for robustness against missing modalities: UniBEV can operate on LiDAR plus camera input, but also on LiDAR-only or camera-only input without retraining. To facilitate its detector head to handle different input combinations, UniBEV aims to create well-aligned Bird’s Eye View (BEV) feature maps from each available modality. Unlike prior BEV-based multi-modal detection methods, all sensor modalities follow a uniform approach to resample features from the original sensor coordinate systems to the BEV features. We furthermore investigate the robustness of various fusion strategies w.r.t. missing modalities: the commonly used feature concatenation, but also channel-wise averaging, and a generalization to weighted averaging termed Channel Normalized Weights. To validate its effectiveness, we compare UniBEV to state-of-the-art BEVFusion and MetaBEV on nuScenes over all sensor input combinations. In this setting, UniBEV achieves better performance than these baselines for all input combinations. An ablation study shows the robustness benefits of fusing by weighted averaging over regular concatenation, and of sharing queries between the BEV encoders of each modality. Our code is available at https://github.com/tudelft-iv/UniBEV.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalities


    Beteiligte:
    Wang, Shiming (Autor:in) / Caesar, Holger (Autor:in) / Nan, Liangliang (Autor:in) / Kooij, Julian F. P. (Autor:in)


    Erscheinungsdatum :

    02.06.2024


    Format / Umfang :

    4252515 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Learn association for multi-object tracking with multi sensory data and missing modalities

    BLUVSTEIN MAX / ORON SHAUL / SHLOMO BAT EL | Europäisches Patentamt | 2022

    Freier Zugriff

    LEARN ASSOCIATION FOR MULTI-OBJECT TRACKING WITH MULTI SENSORY DATA AND MISSING MODALITIES

    BLUVSTEIN MAX / ORON SHAUL / SHLOMO BAT EL | Europäisches Patentamt | 2020

    Freier Zugriff

    Object velocity detection from multi-modal sensor data

    PRADHAN SABEEK MANI / SLOAN COOPER STOKES | Europäisches Patentamt | 2023

    Freier Zugriff

    Real-Time Bird’s Eye View Multi-Object Tracking system based on Fast Encoders for Object Detection

    Gomez-Huelamo, Carlos / Del Egido, Javier / Bergasa, Luis M. et al. | IEEE | 2020