To avoid the difficulty of collecting accurate traffic flow data, this paper proposes a novel approach for congestion features extraction from traffic video. The approach firstly segments the traffic video into shots and the shot motion content feature is extracted. Then, we extract the key frames applying an improved global k-means clustering algorithm. The last congestion feature of the global optical flow energy is computed based on the key frames. The numerical experiments on traffic surveillance video show the validity and high accuracy for traffic congestion detection using the propose method in this paper


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Feature Extraction Approach of Traffic Congestion from Video



    Erschienen in:

    Advanced Materials Research ; 490-495 ; 1058-1062


    Erscheinungsdatum :

    15.03.2012


    Format / Umfang :

    5 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    An Automatic Recognition Approach for Traffic Congestion States Based on Traffic Video

    Zou, Fu-min / Llao, Lü-chao / Jiang, Xin-hua et al. | ASCE | 2014



    Abnormal Traffic Congestion Recognition Based on Video Analysis

    Liu, Xueli / Gao, Wen / Feng, Dong et al. | IEEE | 2020


    Traffic Lane Congestion Ratio Evaluation by Video Data

    Stetsenko, Inna V. / Stelmakh, Oleksandr | Springer Verlag | 2019