In vehicle detection and tracking methods based on roadside cameras, due to factors such as motion blur, vehicle occlusion, and target scale changes in the video, problems such as missed detection, false detection, and low positioning accuracy may occur during vehicle detection and tracking. This paper proposes to use the improved target detection model YOLOv5s as the target detector, then combined with the classical Deep SORT target tracking method, to achieve end-to-end vehicle detection and tracking. By integrating the attention mechanism with the detection network, and modifying the loss function, the ability of the model to extract features is strengthened, and the final vehicle detection accuracy is 96.7%. During tracking, the vehicle IDs are reduced to 28 times and the operating speed reaches 32 Hz.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Vehicle recognition and tracking method based on roadside perception


    Beteiligte:
    Cao, Wenguan (Autor:in)

    Kongress:

    Third International Conference on Computer Science and Communication Technology (ICCSCT 2022) ; 2022 ; Beijing,China


    Erschienen in:

    Proc. SPIE ; 12506


    Erscheinungsdatum :

    28.12.2022





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    VEHICLE PERCEPTION OF ROADSIDE SHELTERS

    NG CHEUK-HUNG / TRAN DAVID / LEWIS WILLIE | Europäisches Patentamt | 2024

    Freier Zugriff

    Roadside parking vehicle track recognition method and system based on multi-sensor perception

    YAN JUN / ZHANG HENG / XIANG YANPING et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    IMAGE-BASED VEHICLE TRACKING FROM ROADSIDE LIDAR DATA

    J. Zhang / W. Xiao / B. Coifman et al. | DOAJ | 2019

    Freier Zugriff


    Method for evaluating traffic participant perception capability based on roadside perception system

    MA PANKE / ZHANG YI / CHANG SIYANG et al. | Europäisches Patentamt | 2022

    Freier Zugriff