计算机与现代化 ›› 2023, Vol. 0 ›› Issue (05): 117-121.

• 图像处理 • 上一篇    下一篇

改进YOLOv5算法的遥感图像车辆检测

  

  1. (1.东华理工大学信息工程学院,江西 南昌 330013;
    2.东华理工大学江西省核地学数据科学与系统工程技术研究中心,江西 南昌 330013)
  • 出版日期:2023-06-06 发布日期:2023-06-06
  • 作者简介:朱理清(1998—),男,江西赣州人,硕士研究生,研究方向:计算机视觉,图像处理,E-mail: devil_135@163.com; 李祥(1973—),男,江西萍乡人,教授,硕士生导师,博士,研究方向:大数据分析,图像处理,E-mail: tom_lx@126.com。
  • 基金资助:
    江西省核地学数据科学与系统工程技术研究中心开放基金资助项目(JETRCNGDSS201801)

Vehicle Detection of Remote Sensing Images Based on Improved YOLOv5 Algorithm

  1. (1. School of Information Engineering, East China University of Technology, Nanchang 330013, China;
    2. Jiangxi Engineering Technology Research Center of Nuclear Geoscience Data Science and System, East China University of Technology, Nanchang 330013, China)
  • Online:2023-06-06 Published:2023-06-06

摘要: 针对遥感图像中背景复杂目标、车辆小导致的成像模糊的目标漏检问题,提出一种基于YOLOv5s的改进模型。改进模型设计一种新的主干网络结构:改进模型的主干特征提取选用RepVGG网络,同时在主干网络中加入注意力机制CoordAttention来提高模型小目标的感知能力。增加多尺度特征融合,提高改进模型对于小目标的检测精度,边框回归的损失函数选择使用DIoU,帮助改进模型实现更加精准定位。实验结果表明,改进后的YOLOv5模型在遥感图像的目标检测,相较于原始模型在小目标车辆中检测精度提升5.3个百分点,与Faster R-CNN相比mAP提升16.88个百分点。改进后的模型与主流的检测算法相比能有较大的检测精度提升,相较于原始的YOLOv5s模型在遥感图像小车辆检测有更好的检测精度。

关键词: 遥感图像识别, 目标识别, YOLO, 注意力机制, 多尺度特征融合

Abstract: An improved model based on YOLOv5s is proposed for the problem of target miss detection in remote sensing images with complex targets in the background and blurred imaging due to small vehicles. A new backbone network structure is designed for the improved model: RepVGG network is selected for the backbone feature extraction of the improved model, while an attention mechanism, CoordAttention, is added to the backbone network to improve the perception capability of the model for small targets. Multi-scale feature fusion is added to improve the detection accuracy of the improved model for small targets, and the loss function of border regression is chosen to use DIoU to help the improved model achieve more accurate localization. After experiments, it is demonstrated that the improved YOLOv5 model improves the detection accuracy by 5.3 percentage points for target detection in remote sensing images compared to the original model in small target vehicles, and improves the mAP by 16.88 percentage points compared to Faster R-CNN. The improved model can have a larger detection accuracy improvement compared with the mainstream detection algorithms, and has a better detection accuracy than the original YOLOv5s model for small vehicle detection in remote sensing images.

Key words: remote sensing image recognition, target recognition, YOLO, attention mechanisms, multi-scale feature fusion