With the rapid development of remote sensing technology, remote sensing images play an important role in the agricultural field, geological field, and natural disaster detection. The size of aircraft in complex scenes in remote sensing images is extremely small, and aircraft of different models have similar shapes. Therefore, improving the accuracy of aircraft target recognition is a challenging task. We propose an improved aircraft small target recognition method based on yolov5, which can improve the recognition accuracy of aircraft targets while ensuring the speed of the model. The specific content is as follows: To address the problem of lack of remote sensing aircraft training sets, we use existing public remote sensing images to combine with aircraft model images. Most of the aircraft models only occupy a dozen to twenty pixels in the 1k*1k image, and perform Scale the generated data set; in order to better combine features of different scales and obtain higher-level feature fusion, introduce the BiFPN module with more residual connections and more complete feature fusion; use the SE attention mechanism to learn the weights of different features , extract information that is more important for detection and improve model performance; in view of the small size of the aircraft, a detection method based on Wasserstein distance such as NWD (Normalized Wasserstein Distance) is selected as the loss function.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Remote sensing aircraft small object detection algorithm based on YOLOv5


    Contributors:
    Bilas Pachori, Ram (editor) / Chen, Lei (editor) / Qiu, Yijuan (author) / Xue, Jiefeng (author) / Zhang, Jie (author) / Jiang, Ping (author) / Zhang, Gang (author) / Lei, Tao (author)

    Conference:

    International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024) ; 2024 ; Guangzhou, China


    Published in:

    Proc. SPIE ; 13180


    Publication date :

    2024-06-13





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Ship Remote Sensing Target Recognition Based on YOLOV5

    Hao, Ning / Li, Yunwei / Ma, Yusen et al. | Springer Verlag | 2024



    Military Aircraft Detection Using YOLOv5

    Ajay Kumar Goud, P. / Mohit Raj, G. / Rahul, K. et al. | Springer Verlag | 2023


    Research on UAV Object Detection Algorithm Based on CSPCM-YOLOv5

    Xiong, Qiaohui / Shan, Liang / Ma, Qiang et al. | Springer Verlag | 2024