Different weather and light conditions will affect the detection of pavement sag. And the camera field of view is limited, can not fully cover the entire highway road surface, resulting in higher difficulty in road sag detection. Therefore, a rapid visual detection method for highway pavement sag based on improved Yolov7-tiny is proposed. The structure elements are determined, and the small noise points in the image are removed by etching operation, and the morphology of the highway surface is completed. Input the processed highway pavement sag image into YOLOv7-tiny network, improve the input module and backbone network, and output the irregular shape of the sag image target. Fuzzy C-Means (FCM) clustering algorithm is introduced and objective function is established to realize the morphological feature visual detection of highway pavement depression. The experimental results show that: The method has smaller entropy, larger fuzzy coefficient, higher peak signal-to-noise ratio, and clearer features of pavement depression images.


    Access

    Download


    Export, share and cite



    Title :

    Rapid visual detection method of highway pavement sag based on improved Yolov7-tiny


    Contributors:


    Publication date :

    2024




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown





    Freeway vehicle detection on improved YOLOv7

    Gong, Shaojie / Mao, Kun / Yuan, Haifeng et al. | SPIE | 2023


    YOLOv7-RDD: A Lightweight Efficient Pavement Distress Detection Model

    Ning, Zhipeng / Wang, Hui / Li, Shenglin et al. | IEEE | 2024


    Improved YOLOv7 Target Detection Algorithm Based on UAV Aerial Photography

    Zhen Bai / Xinbiao Pei / Zheng Qiao et al. | DOAJ | 2024

    Free access

    Automatic driving risk pre-judgment system and method based on improved YOLOV7-Tiny and SS-LSTM in V2X environment

    ZHAO HONGZHUAN / ZHANG JIKANG / PAN JIAWEN et al. | European Patent Office | 2024

    Free access