At present, most highways in China have established full-coverage video systems, but highway traffic event detection still uses alarms and manual inspections. Especially, the high incidence of nighttime freeway traffic events makes inspection difficult, which is a difficult point in freeway emergency management. We develop a nighttime traffic event detection algorithm that can be integrated into existing highway video surveillance systems, which has three components: video initial processing, vehicle detection and vehicle tracking speed measurement. Among them, the Hom-Schunck optical flow algorithm is used for vehicle detection and Deepsort’s multi-target vehicle tracking algorithm is used for vehicle tracking and speed measurement. Finally comparing the vehicle detection part using background difference method, yolo algorithm and the algorithm in this paper, the algorithm in this paper has higher detection accuracy, while the detection speed meets the system working requirements.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on highway night traffic event detection method based on video processing


    Contributors:
    Bao, Lixia (author) / Wang, Qiulan (author) / Zuo, Shuxia (author) / Jiang, Yan (author) / Mo, Xianglun (author)


    Publication date :

    2021-10-01


    Size :

    1078924 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Traffic event-oriented highway traffic control effect evaluation method

    ZHANG XIAOCHUN / LIN TAO / ZHUANG LIJIAN et al. | European Patent Office | 2020

    Free access

    Traffic event video detection system

    HE SONGSONG / TAO JIANWEN / DAN YUFANG et al. | European Patent Office | 2021

    Free access

    Traffic event detection method fusing radar video

    LI ZHONGCHENG / HUANG HAILANG / HUANG SHENG | European Patent Office | 2020

    Free access

    Towards Large-Scale Video-Based Highway Traffic Monitoring

    Spoecklberger, Johannes / Micorek, Jakub / Possegger, Horst et al. | IEEE | 2023