摘要
针对输电线路巡检中可能存在拍摄图像质量不高的问题,以及线路缺陷目标小而分布密集而导致传统方法检测精度不高的问题,提出一种基于超分辨率重建与多尺度特征融合的输电线路缺陷检测方法。首先,使用超分辨率网络对巡检图像进行重建,提升清晰度,丰富图像中包含的特征信息;然后使用改进的YOLOX网络检测巡检图像中的缺陷,在主干网络中嵌入卷积块注意力机制,强化模型对重叠小目标的定位能力;为进一步提升小目标的检测能力,在YOLOX的特征融合网络中新增浅层检测尺度进行特征融合;最后,通过使用CIOU优化边界框损失函数提升模型收敛能力,降低缺陷目标的漏检率。实验结果表明,所提方法能在提升巡检图像质量的基础上对输电线路缺陷准确地检测,精度达到93.27%,相比SSD等经典模型,对小而密集的缺陷目标有着更强的提取能力和鲁棒性。
Aiming at the problem that the quality of the captured image may be poor in the inspection of transmission lines, and the problem that the detection accuracy of traditional methods is not high due to the line defect that the targets are small and densely distributed, a transmission line defect detection method based on super-resolution reconstruction and multi-scale feature fusion is proposed. First, the super-resolution network is used to reconstruct the inspection image, improve the clarity and enrich the feature information contained in the image. Then the improved YOLOX network is used to detect defects in the inspection image, and the convolution block attention mechanism is embedded in the backbone network to strengthen the positioning ability of the model for overlapping small targets. In order to further improve the detection ability of small targets, a shallow detection scale is added to YOLOX’s feature fusion network for feature fusion. Finally, by using CIOU to optimize the loss function of the bounding box, improve the convergence ability of the model and reduce the missed detection rate of the defect targets. The experimental results show that the proposed method can accurately detect the transmission line defects on the basis of improving the inspection image quality, with an accuracy of 93.27%. Compared with classical models such as SSD, it has stronger extraction ability and robustness for small and dense defect targets.
作者
刘兰兰
万旭东
汪志刚
张建
彭昊
杨嘉妮
Liu Lanlan;Wan Xudong;Wang Zhigang;Zhang Jian;Peng Hao;Yang Jiani(Live Inspection and Intelligent Operation Technology State Grid Corporation Laboratory,Changsha 421000,China;Hunan Province Key Laboratory of Intelligent Live Working Technology and Equipment(Robot),Changsha 421000,China;College of Electrical Engineering and New Energy,China Three Gorges University,Yichang 443002,China)
出处
《电子测量与仪器学报》
CSCD
北大核心
2023年第1期130-139,共10页
Journal of Electronic Measurement and Instrumentation
基金
智能带电作业技术及装备(机器人)湖南省重点实验室开放基金(2021KZD3001)
湖北省输电线路工程技术研究中心开放课题(2019KXL05)项目资助
关键词
输电线路缺陷检测
超分辨率
卷积块注意力
多尺度特征融合
transmission line defect detection
super resolution
convolutional block attention
multiscale feature fusion
作者简介
刘兰兰,2009年于中南大学获得学士学位,2014年于中国科学院大学获得博士学位,现为国网湖南省电力有限公司超高压输电公司高级工程师,主要研究方向为智能输电运维。E-mail:0603050307@163.com;通信作者:万旭东,2020年于湖北工业大学获得学士学位,现为三峡大学硕士生,主要研究方向为输电线路智能检测和电力深度视觉。E-mail:416208625@qq.com
