By comparing multiple target detection algorithms, combined with the particularity of the airport scene, finally an algorithm based on YOLOv5 was selected for airport multi-target detection.. After tuning the parameters according to the loss function and the mean average precision in training, a target detection model adapted to the airport scene is obtained. The data was collected from a high-definition camera at Chengdu Shuangliu Airport, and about 3000 highdefinition pictures were obtained by intercepting video frames. Then the experiment use "LabelImg" software to annotate the data to get the VOC data set. Experimental results show that the average accuracy of the algorithm can reach 85.77%, and it can effectively detect aircraft on the airport scene.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multi-target Detection in Airport Scene Based on Yolov5


    Contributors:
    Kun, Yan (author) / Man, Hua (author) / Yanling, Li (author)


    Publication date :

    2021-10-20


    Size :

    1107597 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    An improved Yolov5-based algorithm for pavement disease detection in airport flight areas

    Wang, Sibo / Hao, Shougang / Zhang, Ping et al. | SPIE | 2025


    Vehicle Target Detection in Day-Night Mode Based on YOLOv5

    Li, Fulian / He, Zejiang / Yu, Yue | IEEE | 2023


    Multi-scale Small Target Detection for Indoor Mobile Rescue Vehicles Based on Improved YOLOv5

    Li, Maoyue / Yang, Tenghui / Xu, Shengbo et al. | Springer Verlag | 2024


    Multi-scale Small Target Detection for Indoor Mobile Rescue Vehicles Based on Improved YOLOv5

    Li, Maoyue / Yang, Tenghui / Xu, Shengbo et al. | Springer Verlag | 2024