摘要
为提高变电站设备缺陷的检测精度,保障变电站运行安全,提出一种基于改进YOLOv4的缺陷检测算法.不同于原始YOLOv4,该算法使用一维卷积替代全连接来优化CBAM卷积注意力模块,然后将其嵌入主干网络中以增强特征提取能力;同时,在特征融合中应用空洞卷积扩大感受野,聚合更广的语义信息.该算法在现场拍摄的样本集上进行测试, mAP可达到86.97%,相比原始YOLOv4提高了2.78%.实验结果表明,本文提出的YOLOv4改进算法能够提升网络性能,更好地应用于变电站设备缺陷检测任务.
To increase the defect detection accuracy on substation equipment and thus ensure the operation safety of the substation, this study proposes a defect detection algorithm based on an improved YOLOv4. Unlike the original YOLOv4,the new algorithm replaces the fully connected layers with one-dimensional convolution to optimize the convolutional block attention module(CBAM), which is then embedded into the backbone network to enhance the feature extraction ability. Meanwhile, dilated convolution is used in feature fusion layers for expanding the receptive field and aggregating broader semantic information. The algorithm is tested on images captured in real substation scenes and achieves a mean average precision(mAP) of 86.97%, an increase of 2.78% on that of the original YOLOv4. Experimental results show that the proposed algorithm can improve the network performance and is thus more suitable for defect detection on substation equipment.
作者
陈婷
周旻
韩勤
张湘
茅耀斌
CHEN Ting;ZHOU Min;HAN Qin;ZHANG Xiang;MAO Yao-Bin(School of Automation,Nanjing University of Science and Technology,Nanjing 210094,China;Zhejiang Huayun Information Technology Co.Ltd.,Hangzhou 310030,China)
出处
《计算机系统应用》
2022年第6期245-251,共7页
Computer Systems & Applications
关键词
YOLOv4
缺陷检测
CBAM注意力
空洞卷积
特征融合
卷积神经网络
YOLOv4
defect detection
convolutional block attention module(CBAM)attention
dilated convolution
feature fusion
convolutional neural networks(CNN)
作者简介
通信作者:茅耀斌,E-mail:myb_nust@126.com。
