The robustness of semantic segmentation on edge cases of traffic scene is a vital factor for the safety of intelligent transportation. However, most of the critical scenes of traffic accidents are extremely dynamic and previously unseen, which seriously harm the performance of semantic segmentation methods. In addition, the delay of the traditional camera during high-speed driving will further reduce the contextual information in the time dimension. Therefore, we propose to extract dynamic context from event-based data with a higher temporal resolution to enhance static RGB images, even for those from traffic accidents with motion blur, collisions, deformations, overturns, etc. Moreover, in order to evaluate the segmentation performance in traffic accidents, we provide a pixel-wise annotated accident dataset, namely DADA-seg, which contains a variety of critical scenarios from traffic accidents. Our experiments indicate that event-based data can provide complementary information to stabilize semantic segmentation under adverse conditions by preserving fine-grained motion of fast-moving foreground (crash objects) in accidents. Our approach achieves +8.2% performance gain on the proposed accident dataset, exceeding more than 20 state-of-the-art semantic segmentation methods. The proposal has been demonstrated to be consistently effective for models learned on multiple source databases including Cityscapes, KITTI-360, BDD, and ApolloScape.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Exploring Event-Driven Dynamic Context for Accident Scene Segmentation


    Beteiligte:
    Zhang, Jiaming (Autor:in) / Yang, Kailun (Autor:in) / Stiefelhagen, Rainer (Autor:in)


    Erscheinungsdatum :

    01.03.2022


    Format / Umfang :

    4219672 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Unsupervised scene segmentation using sparse coding context

    Liu, Y. C. / Chen, H. T. | British Library Online Contents | 2013


    VEHICLE ACCIDENT SCENE INFORMATION UNIT

    ZELENSKIJ STANISLAV EVGENEVICH / KOZYREV ALEKSANDR NIKOLAEVICH / ERMAKOV PAVEL IGOREVICH | Europäisches Patentamt | 2017

    Freier Zugriff

    Accident scene anti-intrusion system

    ZHANG CHENGHUI | Europäisches Patentamt | 2015

    Freier Zugriff

    Accident Scene Diagramming Using New Photogrammetric Technique

    Kerr, Richard / Fenton, Stephen | SAE Technical Papers | 1997


    Construction method of traffic accident scene file

    YANG FENGMAN / SONG XIANGHUI / LIU NAN et al. | Europäisches Patentamt | 2024

    Freier Zugriff