Early detection of incidents is a key step to reduce incident related congestion. State Department of Transportation (DoTs) usually install a large number of Close Circuit Television (CCTV) cameras in freeways for traffic surveillance. In this study, we used semi-supervised techniques to detect traffic incident trajectories from the cameras. Vehicle trajectories are identified from the cameras using state-of-the-art deep learning based You Look Only Once (YOLOv3) classifier and Simple Online Realtime Tracking (SORT) is used for vehicle tracking. Our proposed approach for trajectory classification is based on semi-supervised parameter estimation using maximum-likelihood (ML) estimation. The ML based Contrastive Pessimistic Likelihood Estimation (CPLE) attempts to identify incident trajectories from the normal trajectories. We compared the performance of CPLE algorithm to traditional semi-supervised techniques Self Learning and Label Spreading, and also to the classification based on the corresponding supervised algorithm. Results show that approximately 14% improvement in trajectory classification can be achieved using the proposed approach.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Freeway Traffic Incident Detection from Cameras: A Semi-Supervised Learning Approach


    Beteiligte:


    Erscheinungsdatum :

    2018-11-01


    Format / Umfang :

    2685845 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Continuous Learning Framework for Freeway Incident Detection

    Peeta, S. / Das, D. / National Research Council; Transportation Research Board | British Library Conference Proceedings | 1998


    Incorporating Neural Network Traffic Prediction into Freeway Incident Detection

    Teng, H. / Martinelli, D. R. / Taggart, B. T. et al. | British Library Conference Proceedings | 1999