With the rapid development of remote sensing technology, remote sensing target detection faces many problems; for example, there is still no good solution for small targets with complex backgrounds and simple features. In response to the above, we have added dynamic snake convolution (DSC) to YOLOv7. In addition, SPPFCSPC is used instead of the original spatial pyramid pooling structure; the original loss function was replaced with the EIoU loss function. This study was evaluated on UAV image data (VisDrone2019), which were compared with mainstream algorithms, and the experiments showed that this algorithm has a good average accuracy. Compared to the original algorithm, the mAP0.5 of the present algorithm is improved by 4.3%. Experiments proved that this algorithm outperforms other algorithms.


    Access

    Download


    Export, share and cite



    Title :

    Improved YOLOv7 Target Detection Algorithm Based on UAV Aerial Photography


    Contributors:
    Zhen Bai (author) / Xinbiao Pei (author) / Zheng Qiao (author) / Guangxin Wu (author) / Yue Bai (author)


    Publication date :

    2024




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown