摘要
针对现有目标检测算法在复杂背景下绝缘子缺陷检测中容易出现漏检、误检和检测效率低等问题,改进YOLOv5s网络以提高绝缘子缺陷检测精度和速度.采用K-means++聚类分析绝缘子数据集,确定网络预设锚框尺寸;利用Hard-Swish激活函数替换主干网络第3、 5、 7层卷积模块的SiLU激活函数,并添加卷积注意力机制(CBAM),提高网络泛化能力;在主干网络与颈部网络间的跳跃链接添加CBAM,增强图像特征提取能力;利用交叉卷积替换颈部网络特征融合模块的残差结构,减少网络参数,提高检测速度.实验结果表明:基于改进YOLOv5s网络的绝缘子缺陷检测精度和速度分别为88.6%和69.4帧/s,优于Faster R-CNN、YOLOv3、YOLOv4、常规YOLOv5s等主流网络,满足绝缘子缺陷检测要求.
The YOLOv5s network was improved aiming at the problem of missed detection,false detection and low efficiency of existing object detection algorithms for insulator defects in complex backgrounds.K-means++clustering was used to analyze the insulator dataset to determine the anchor box size preset by the network.The SiLU activation function of convolution module in the third,fifth,and seventh layers of the backbone network was replaced by Hard-Swish activation function,and the convolutional block attention mechanism(CBAM)was added to improve the network generalization ability.CBAMs were added to the skip links between backbone network and neck network to enhance the ability of image feature extraction.Moreover,the residual structure of feature fusion module of the neck network was replaced by the cross convolution to reduce the network parameters and improve the detection speed.The experimental results demonstrated that the detection accuracy and speed for the insulator defect by the improved YOLOv5s network were 88.6%and 69.4 frames per second,respectively,which were better than those of the popular networks such as Faster R-CNN,YOLOv3,YOLOv4 and regular YOLOv5s.The improved YOLOv5s network meets the requirements of insulator defect detection.
作者
李运堂
张坤
李恒杰
朱文凯
金杰
章聪
王冰清
OPPONG Francis
LI Yuntang;ZHANG Kun;LI Hengjie;ZHU Wenkai;JIN Jie;ZHANG Cong;WANG Bingqing;OPPONG Francis(College of Mechanical and Electrical Engineering,China Jiliang University,Hangzhou 310018,China)
出处
《浙江大学学报（工学版）》
EI
CAS
CSCD
北大核心
2024年第12期2469-2478,2499,共11页
Journal of Zhejiang University：Engineering Science
基金
浙江省属高校基本科研业务费专项资金(2020YW29)。
关键词
YOLOv5s
绝缘子缺陷
激活函数
卷积注意力机制
交叉卷积
YOLOv5s
insulator defect
activation function
convolutional block attention mechanism
cross convolution
