In this paper, the problem of detecting accidents using speed sensors distributed spatially on a freeway is considered. Due to the significant impact of road accidents on health and development, early and accurate detection of accidents is crucial. To address this issue, a novel Bayesian quickest change detection formulation is introduced, which considers both average detection delay and false alarm rate. The optimum strategy is derived via dynamic programming and shown to compare a recursively computed statistic with a function of false alarm to identify accidents as they happen. Considering that post–accident conditions are typically not known, two methods are proposed that recursively estimate multiple unknown parameters during the accident detection process. Further, four aggregation methods are proposed to improve performance exploiting spatial correlations between sensors. Extensive evaluation results demonstrate improvement up to 65.2% and 87.2% in average detection delay and false alarm rate, respectively, against prior work.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Near Real-Time Freeway Accident Detection




    Erscheinungsdatum :

    2022-02-01


    Format / Umfang :

    3457293 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Analysis of Freeway Accident Detection

    Corby, M. J. / Saccomanno, F. F. | Transportation Research Record | 1997


    Analysis of Freeway Accident Detection

    Corby, M. J. / Saccomanno, F. F. / National Research Council; Transportation Research Board | British Library Conference Proceedings | 1997


    Analysis of Freeway Accident Detection

    Corby, M.J. | Online Contents | 1997


    Real Time Freeway Incident Detection

    M. Motamed / R. Machemehl | NTIS | 2014


    Non-Blind Area Real-Time Monitoring and Alarming System for Accident on Freeway

    TONG XINGLIN / WANG QINYU / DENG CHENGWEI et al. | Europäisches Patentamt | 2023

    Freier Zugriff