基于改进YOLOv7的输电线路多类缺陷目标检测  

Multi-Class Defect Target Detection for Transmission Lines Based on Improved YOLOv7

作　　者：毕含嘉 杨楚睿 王小雨 黄悦华[1] BI Hanjia;YANG Churui;WANG Xiaoyu;HUANG Yuehua(College of Electrical Engineering and New Energy,China Three Gorges University,Yichang 443002,China;State Grid Hubei Yichang Yiling Power Supply Company,Yichang 443000,China)

机构地区：[1]三峡大学电气与新能源学院,湖北宜昌443002 [2]国网湖北省宜昌市夷陵区供电公司,湖北宜昌443000

出　　处：《电子科技》2025年第4期16-24,共9页Electronic Science and Technology

基　　金：国家自然科学基金(52007103)。

摘　　要：针对在复杂背景下输电线路多尺度缺陷目标检测精度较低的问题,文中提出一种基于改进YOLOv7(You Only Look Once version 7)的输电线路多类缺陷目标检测模型。对于复杂背景造成缺陷目标较低的问题,在Backbone部分引入改进的Swin Transformer模块,通过使用多头注意力机制提升对全局特征的提取效果来提高模型的检测精度。对于待检测目标的多尺度特性,在特征金字塔基础上引入自适应特征融合模块,提升了Neck部分特征融合网络对多类不同尺度缺陷目标的检测能力。使用SIoU(Structured Intersection over Union)损失函数在提高预测框回归精度的同时加快了模型的收敛。实验结果表明,相较于YOLOv5、YOLOv7和Faster R-CNN(Faster Region with Convolutional Neural Network)模型,改进YOLOv7模型具有较高的检测精度,其平均检测精度可达96.4%,检测速度为29.6 frame·s^(-1),能够为输电线路多类缺陷目标检测提供参考。In view of the low detection accuracy of multi-scale defect targets in transmission lines under complex background,an improved YOLOv7(You Only Look Once version7)defect target detection model for transmission lines is proposed.To solve the problem of low defect targets caused by complex background,an improved Swin Transformer module is introduced in the Backbone part to improve the detection accuracy of the model using multi-head attention mechanism to improve the effect of global feature extraction.According to the multi-scale characteristics of the target to be detected,an adaptive feature fusion module is introduced on the basis of the feature pyramid to improve the detection ability of the Neck partial feature fusion network on multiple defect targets of different scales.SIoU(Structured Intersection over Union)loss function is used to improve the accuracy of prediction frame regression and accelerate the model convergence.Experimental results show that compared with YOLOv5,YOLOv7 and Faster R-CNN(Faster Region Proposal Convolutional Neural Network)models,the improved YOLOv7 model has higher detection accuracy,with an average detection accuracy of 96.4%and a detection speed of 29.6 frame·s^(-1),which can provide reference for the detection of multiple types of defect targets of transmission lines.

关 键 词：YOLOv7 深度学习 输电线路缺陷检测 小目标检测 多尺度融合 Swin Transformer β-dropout 自适应特征融合 损失函数 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]