Insulator Defect Detection Algorithm for Multi-scale Feature Extraction Based on Improved YOLOv7

SUN Hong; GUO Yihan; LEI Jingfa; ZHAO Ruhai; LI Yongling; ZHANG Miao

doi:10.13296/j.1001-1609.hva.2025.06.012

您当前的位置：

首页 >

文章列表页 >

Insulator Defect Detection Algorithm for Multi-scale Feature Extraction Based on Improved YOLOv7

Research & Analysis | 更新时间：2025-06-12

- Insulator Defect Detection Algorithm for Multi-scale Feature Extraction Based on Improved YOLOv7
- High Voltage Apparatus Vol. 61, Issue 6, Pages: 102-112(2025)
- 作者机构：
  
  1.安徽建筑大学机械与电气工程学院，合肥　 230601
  2.工程机械智能制造安徽省教育厅重点实验室，合肥　 230601
  3.过程装备与控制工程四川省高校重点实验室，四川　自贡　 643000
- 作者简介：
- 基金信息：
  
  Anhui Provincial Key Research and Development Plan Project, China(1804a09020009);Anhui University Natural Science Research Major Project and Key Project, China(J2021ZA0068;KJ2021A1060;2023AH040036);Anhui University Collaborative Innovation Project, China(GXXT-2022-019;GXXT2023-006;GXXT-2023-025);Process Equipment and Control Engineering Open Fund Project of Key Laboratory of Sichuan University, China(GK202101;GK202308)
- DOI：10.13296/j.1001-1609.hva.2025.06.012
  CLC：
- Received：20 November 2024，
  
  Revised：20 March 2025，
  
  Published：16 June 2025
- 稿件说明：
移动端阅览
SUN Hong, GUO Yihan, LEI Jingfa, et al. Insulator Defect Detection Algorithm for Multi-scale Feature Extraction Based on Improved YOLOv7[J]. High voltage apparatus, 2025, 61(6): 102-112.
DOI：

SUN Hong, GUO Yihan, LEI Jingfa, et al. Insulator Defect Detection Algorithm for Multi-scale Feature Extraction Based on Improved YOLOv7[J]. High voltage apparatus, 2025, 61(6): 102-112. DOI： 10.13296/j.1001-1609.hva.2025.06.012.

摘要

针对绝缘子图像缺陷尺寸小、背景干扰因素多、难易样本不平衡等问题，提出了一种多尺度融合的YOLOv7（MSF-YOLOv7）算法，并将其应用于输电线路绝缘子的缺陷检测。首先，通过多尺度卷积块注意力模块（multi scale-convolution block attention module，MS-CBAM），深度聚合带有丰富语义信息的特征图，提升网络对不同尺度目标的检测性能；其次，在主干网络利用新开发的全局空间金字塔池化（global spatial pyramid pooling-fast，GSPPF）模块增加全局背景信息，以减轻复杂背景所带来的影响；针对样本分布不平衡的问题，引入Focaler-CIoU损失函数聚焦不同缺陷目标，加快模型的收敛速度。实验结果表明，文中提出的MSF-YOLOv7模型

mAP

达到88.1%，精确度和召回率达到90.3%和83.1%，较YOLOv7算法分别提升了6.3%、7.9%和6.3%，同时参数量与浮点计算量分别降低了13.38%和2.95%。

Abstract

In view of such issues as small defect sizes in insulation images

abundant background interference factors and imbalanced difficulty and easy sample of insulator

a multi-scale fusion YOLOv7 (MSF-YOLOv7) algorithm is proposed and applied to the defect detection of insulator of power transmission lines. Firstly

the multi-scale convolution block attention module (MS-CBAM) is introduced to deeply aggregate feature maps with rich semantic information

enhancing the network's detection performance for target at different scales. Then

a newly developed global spatial pyramid pooling-fast (GSPPF) module is used in the backbone network to incorporate global background information

mitigating the influence of complex backgrounds. In view of imbalanced sample distribution

the Focaler-CIoU loss function is introduced to focus on different defect targets

speeding up the model's convergence rate. The experimental results indicate that the

mAP

of MSF-YOLOv7 model proposed in this paper is up to 88.1%

the precision and recall rates are up to 90.3% and 83.1%

which are 6.3%

7.9% and 6.3% higher than those of the YOLOv7 algorithm and

at the same time

the number of parameters and GFLOPs are reduced by 13.38% and 2.95%

respectively.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Multi-type Defect Detection of Insulator for Transmission Line Based on GE-YOLO Algorithm

Multiple Defect Detection of Insulators Based on Improved YOLOv5 Algorithm

Super-resolution Reconstruction of Infrared Image of Transmission Line Insulator Based on Lightweight Residual in Residual Dense Net

Research on Multi Type Defect Detection of Transmission Line Insulators Based on GE-YOLO Algorithm

Related Author

WANG Qiang

FENG Yuntao

ZHOU Chao

WU Zhenliao

WU Zhengping

SUN Shuifa

WU Tian

YANG Wei

Related Institution

College of Electrical and New Energy, China Three Gorges University

Hubei Provincial Engineering Research Center of Intelligent Energy Technology

College of Electrical Engineering and New Energy, China Three Gorges University

Hubei Provincial Engineering Technology Research Center for Power Transmission Line, Three Gorges University

College of Computer and Information, China Three Gorges University

⁰