计算机与现代化 ›› 2025, Vol. 0 ›› Issue (08): 82-88.doi: 10.3969/j.issn.1006-2475.2025.08.012

• 图像处理 • 上一篇    下一篇

基于YOLOv5的双主干网络绝缘子缺陷检测算法

  


  1. (1.国网江苏省电力有限公司,江苏 南京 210000; 2.中国电力科学研究院有限公司,北京 100192;
    3.南京信息工程大学数字取证教育部工程研究中心,江苏 南京 210044) 
  • 出版日期:2025-08-27 发布日期:2025-08-28
  • 作者简介: 作者简介:高莉莎(1986—),女,江苏南京人,高级工程师,研究方向:计算机视觉,缺陷检测,E-mail: sun_gls@163.com; 通信作者:朱跃飞(1998—),男,江苏连云港人,硕士研究生,研究方向:目标检测,E-mail: zhuyuefei@nuist.edu.cn。
  • 基金资助:
     基金项目:国家电网公司总部科技项目(5700-202318309A-1-1-ZN)
     

Dual-backbone Network Insulator Defect Detection Algorithm Based on YOLOv5


  1. (1. State Grid Jiangsu Electric Power Co., Ltd., Nanjing 210000, China; 2. China Electric Power Research Institute Co., Ltd., Beijing 100192, China; 3. Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology, Nanjing 210044, China)
  • Online:2025-08-27 Published:2025-08-28

摘要: 摘要:当前的绝缘子缺陷检测算法存在特征提取不够充分、小目标检测效果差、算法整体的性能不平衡等问题。针对上述问题,本文提出一种基于YOLOv5的双主干网络绝缘子缺陷检测算法。首先,本文设计一种新型适用于YOLOv5的双主干特征提取网络GELAN-Ghost,该模块在保持轻量化的同时可以更加充分地提取特征信息;其次,利用倒置残差结构的思想,在算法的颈部网络部分中设计一种即插即用的高效多尺度注意力模块iEMA;最后,设计一种新型动态检测头DynamicHeadv3替代原有的检测头,以提取更丰富的特征并增强模型的感知能力。实验结果表明,改进后的模型精度提升了1.4百分点,参数量和计算量分别下降了46%和33%,检测速度也得到了一定的提升,性能达到了较好的平衡,更符合无人机和边缘端绝缘子缺陷检测的需求。


关键词: 关键词:绝缘子缺陷检测, YOLOv5, 双主干网络, iEMA注意力机制, 动态检测头

Abstract:
Abstract: The current insulator defect detection algorithm has problems such as insufficient feature extraction, poor small target detection effect, and unbalanced overall algorithm performance. To address the above problems, this paper proposes a dual-trunk network insulator defect detection algorithm based on YOLOv5. Firstly, this paper designs a new dual-trunk feature extraction network GELAN-Ghost suitable for YOLOv5. This module can more fully extract feature information while maintaining lightweight. Secondly, using the idea of inverted residual structure, a plug-and-play efficient multi-scale attention module iEMA is designed in the neck network part of the algorithm. Finally, a new dynamic detection head DynamicHeadv3 is designed to replace the original detection head to extract richer features and enhance the perception ability of the model. The experimental results show that the improved model has an accuracy improvement of 1.4 percentage points, a parameter amount and a computational amount reduced by 46% and 33% respectively, and the detection speed has also been improved to a certain extent. The performance has achieved a good balance, which is more in line with the needs of drone and edge insulator defect detection. 

Key words: Key words: insulator defect detection, YOLOv5, dual-backbone network, iEMA attention mechanism, dynamic detection head

中图分类号: