Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (10): 253-261.DOI: 10.3778/j.issn.1002-8331.2212-0045

• Graphics and Image Processing • Previous Articles     Next Articles

Improved YOLOv5 for Remote Sensing Image Detection

LIU Tao, DING Xueyan, ZHANG Bingbing, ZHANG Jianxin   

  1. 1.School of Computer Science and Engineering, Dalian Minzu University, Dalian, Liaoning 116600, China
    2.Institute of Machine Intelligence and Biological Computing, Dalian Minzu University, Dalian, Liaoning 116600, China
    3.School of Information and Communication Engineering, Dalian University of Technology, Dalian, Liaoning 116024, China
  • Online:2023-05-15 Published:2023-05-15

改进YOLOv5的遥感图像检测方法

刘涛,丁雪妍,张冰冰,张建新   

  1. 1.大连民族大学 计算机科学与工程学院,辽宁 大连 116600
    2.大连民族大学 机器智能与生物计算研究所,辽宁 大连 116600
    3.大连理工大学 信息与通信工程学院,辽宁 大连 116024

Abstract: Focusing on that YOLOv5 fails to take into account the issues of poor detection effects, false detection as well as omission caused by complex background information, small detection targets and low percentage of target semantic information in remote sensing image object detection, this paper proposes an improved YOLOv5 for remote sensing target detection. Firstly, a lightweight channel attention block is embedded to the C3 module of feature extraction and fusion module, aiming at enhancing the abilities of local feature extraction and fusion. Secondly, to enhance the multi-scale feature representation capability, a fine-level detection layer that fuses shallow semantic information is added, which helps to detect small targets. Finally, the Copy-Paste data augmentation is leveraged to enrich the diversity of training samples, which further solves the rate problem of high background information and low target area without introducing extra computation cost. Experimental results show that the improved YOLOv5 achieves 0.757 and 0.759 mAP values on the DOTA and DIOR datasets, respectively. It outperforms YOLOv5 by 0.017 and 0.059 gains, as well as obtains obvious accuracy improvements compared with other typical methods, demonstrating the effectiveness of the improved YOLOv5.

Key words: YOLOv5, remote sensing, object detection, attention mechanism, data augmentation

摘要: 针对YOLOv5在遥感图像目标检测中未能考虑到遥感图像背景复杂、检测目标较小且图像中目标语义信息占比过低导致的检测效果不佳和易出现误检漏检等问题,提出了一种改进YOLOv5的遥感图像目标检测方法。将轻量级的通道注意力机制引入到原始YOLOv5的特征提取和特征融合网络的C3模块中,以提升网络局部特征捕获与融合能力;强化对遥感图像的多尺度特征表达能力,通过增加一个融合浅层语义信息的细粒度检测层来提高对小目标的检测效果;使用Copy-Paste数据增强方法来丰富训练样本数量,在不增加模型计算量的情况下可进一步解决遥感图像背景信息占比过高而目标区域占比过低的问题。实验结果表明,改进YOLOv5在公开的DOTA和DIOR遥感图像数据集上mAP结果分别达到0.757和0.759。该方法较原始YOLOv5可提高0.017和0.059,相比于其他典型遥感目标检测方法在精度上也有所提升,证明了改进YOLOv5方法的有效性。

关键词: YOLOv5, 遥感图像, 目标检测, 注意力机制, 数据增强