电子测量与仪器学报

龙乐云,周腊吾,刘淑琴,黄彪,范凯.改进 YOLOv5 算法下的输电线路外破隐患目标检测研究[J].电子测量与仪器学报,2022,36(11):245-253

改进 YOLOv5 算法下的输电线路外破隐患目标检测研究

Identification of hidden damage targets by external forces basedon domain adaptation and attention mechanism

DOI：

中文关键词: 外力破坏目标检测天气变化注意力机制多尺度域自适应 YOLOv5

英文关键词:external force damage target detection the weather changes attentional mechanism multiscale domain adaptive YOLOv5

基金项目:中国南方电网有限责任公司科技项目（GDKJXM20201984）资助

作者	单位
龙乐云	1. 长沙理工大学电气与信息工程学院
周腊吾	1. 长沙理工大学电气与信息工程学院
刘淑琴	2. 广东电网有限责任公司电力科学研究院
黄彪	1. 长沙理工大学电气与信息工程学院
范凯	1. 长沙理工大学电气与信息工程学院

Author	Institution
Long Leyun	1. School of Electrical & Information Engineering, Changsha University of Science and Technology
Zhou Lawu	1. School of Electrical & Information Engineering, Changsha University of Science and Technology
Liu Shuqin	2. Electric Power Research Institute Guangdong Power Grid
Huang Biao	1. School of Electrical & Information Engineering, Changsha University of Science and Technology
Fan Kai	1. School of Electrical & Information Engineering, Changsha University of Science and Technology

摘要点击次数: 1067

全文下载次数: 1335

中文摘要:

采用图像视频技术对输电线路通道实时监控,通过智能目标检测算法实现外力破坏隐患目标的识别并预警的方法精确率高,近年来被逐渐普及。但在实际环境中,由于图片背景复杂、天气变化(如雾、雨等)等因素,训练数据无法涵盖所有条件, 目标识别算法泛化能力较弱,实际应用中常出现漏报和误报。基于这些问题,采用 YOLOv5 作为本文算法基础,通过数据扩增模拟不同天气,引用自注意力机制(CBAM)增强模型的特征提取能力,并加入多尺度域自适应网络对训练集进行对抗训练,增强模型对不同天气、不同场景的泛化能力。经实验证明,本文所用算法得到的召回率(Recall)达到了 86. 9%,较原算法有明显提升,平均准确率(MAP)高于原 YOLOv5 算法,达到了 92. 2%,能准确的检测出待检外破目标,减少漏检、误检。

英文摘要:

The method of using image and video technology to monitor the transmission channel in real time and using intelligent target detection algorithm to realize the identification and early warning of potential damage caused by external force with high accuracy and has been gradually popularized in recent years. However, in the real conditions, due to the scene change, weather change ( such as fog, rain, etc. ) and other factors, training data cannot cover all conditions, and the algorithm model generalization ability is weak, and there are often missed and false positives in the practical application. Based on these problems, we use the YOLOv5 as based algorithm. This article through the data amplification to simulate different weather, with the domain adaptive network to combat training of the training set, strengthen model generalization ability of the different weather, different scene, citing the attention mechanism ( CBAM) at the same time, strengthen model’s ability to extract features from data. Experiments prove that the Recall obtained by the algorithm in this paper reaches 86. 9%, which is significantly improved compared with the original algorithm, and the average accuracy (MAP) is 92. 2% higher than that of the original YOLOv5 algorithm, which can accurately detect the target to be detected and reduce missed and false detection.

查看全文查看/发表评论下载PDF阅读器