基于轻量级密集残差网络的输电线路绝缘子红外图像的超分辨率重建

吴田; 杨威; 陶雄俊; 王申华; 黎鹏; 普子恒; 方春华

doi:null

您当前的位置：

首页 >

文章列表页 >

基于轻量级密集残差网络的输电线路绝缘子红外图像的超分辨率重建

更新时间：2025-06-18

- 基于轻量级密集残差网络的输电线路绝缘子红外图像的超分辨率重建
- Super-resolution Reconstruction of Infrared Image of Transmission Line Insulator Based on Lightweight Residual in Residual Dense Net
- 高压电器 2025年页码：1-12
- 作者机构：
  
  1.三峡大学电气与新能源学院，湖北　宜昌　 443002
  2.三峡大学湖北省输电线路工程技术研究中心，湖北　宜昌　 443002
  3.中国南方电网有限责任公司超高压输电公司昆明局，昆明　 650000
  4.国网浙江省电力有限公司武义县供电公司，浙江　金华　 321200
- 作者简介：
  
  吴田（1983—），男，博士，高级工程师，主要从事电网智能运检和带电作业（E-mail：wutian_08@163.com）。
  杨威（1999—），男，硕士研究生，主要从事电网智能运检和图像处理（E-mail：weiyang_2021@163.com）。
- 基金信息：
  
  国家自然科学基金资助项目(51807110)
- DOI：
  中图分类号：
- 纸质出版日期：
- 稿件说明：
移动端阅览
吴田, 杨威, 陶雄俊, 等. 基于轻量级密集残差网络的输电线路绝缘子红外图像的超分辨率重建[J/OL]. 高压电器, 2025,1-12.

WU Tian, YANG Wei, TAO Xiongjun, et al. Super-resolution Reconstruction of Infrared Image of Transmission Line Insulator Based on Lightweight Residual in Residual Dense Net[J/OL]. High voltage apparatus, 2025, 1-12.
吴田, 杨威, 陶雄俊, 等. 基于轻量级密集残差网络的输电线路绝缘子红外图像的超分辨率重建[J/OL]. 高压电器, 2025,1-12. DOI：

WU Tian, YANG Wei, TAO Xiongjun, et al. Super-resolution Reconstruction of Infrared Image of Transmission Line Insulator Based on Lightweight Residual in Residual Dense Net[J/OL]. High voltage apparatus, 2025, 1-12. DOI：

摘要

红外成像是检测输电线路绝缘子发热缺陷的一种有效方法，受采集设备和拍摄距离的影响，其分辨率较低，图像中绝缘子目标小，大量数据难以处理。针对红外图像分辨率低的问题，文章提出了一种基于轻量级密集残差网络（lightweight residual in residual dense block，LRRDB）的图像超分辨率重建算法（I-SRGAN），设计一种轻量级的密集残差网络，加深网络的深度以提取到更深层次的特征信息，通过深度可分离卷积减少网络参数量；为了克服网络深度过深存在的过拟合和“梯度爆炸”等问题，采用Wasserstein梯度惩罚保证网络训练的稳定性；并结合自注意力机制（self-attention，SA）自适应调节特征信息的权重，提升网络对重要特征的关注。通过对±800 kV输电线路绝缘子红外图像进行超分辨率重建试验，结果表明：I-SRGAN在峰值信噪比（peak signal-to-noise ratio，

PSNR

）上比SRGAN（super resolution using a generative adversarial network）平均值高3.57%；在结构相似度（structural similarity index measure，

SSIM

）上比双三次插值(BiCubic）方法提高3.90%，比SRCNN（super-resolution convolutional neural network）提高2.68%，比SRGAN提高1.41%，轻量级的加入也使重建时间大大减少，可为输电线路绝缘子红外图像的超分辨率重建提供参考。

Abstract

Infrared imaging is an effective method to detect thermal defects of transmission line insulators. Due to the influence of acquisition equipment and shooting distance

its resolution is low

the insulator target in the image is small

and a large amount of data is difficult to process. To solve the problem of low infrared image resolution

this paper proposes an image super resolution reconstruction algorithm (I-SRGAN) based on Lightweight residual in residual dense block (LRRDB). The depth of the network is deepened to extract deeper feature information

and the number of network parameters is reduced by depth-separable convolution. In order to overcome the problems of overfitting and gradient explosion

Wasserstein gradient penalty is used to ensure the stability of network training. Combined with the self-attention (SA) mechanism

the weight of feature information is adjusted adaptively to enhance the network's attention to important features. Through the super-resolution reconstruction test on the infrared image of insulator of ±800kV transmission line

the results show that: The peak signal-to-noise ratio (

PSNR

) of I-SRGAN is 3.57% higher than the average value of super resolution using

a generative adversarial network (SRGAN). The Structural Similarity Index Measure (

SSIM

) is 3.90% higher than that of BiCubic. Compared with SRCNN (super-resolution convolutional neural network)

it is 2.68% higher than SRGAN (1.41% higher than SRGAN). The lightweight addition also greatly reduces the reconstruction time

which can provide a reference for the super-resolution reconstruction of the infrared image of the transmission line insulator.

关键词

Keywords

references

刘辉 , 张洋 , 李子岳 , 等 . 复合绝缘子内部缺陷微波致热检测方法 [J ] . 高压电器 , 2023 , 59 ( 3 ): 179 - 188 .

LIU Hui , ZHANG Yang , LI Ziyue , et al . Internal defect detection method of composite insulator based on microwave heating [J ] . High Voltage Apparatus , 2023 , 59 ( 3 ): 179 - 188 .

王道累 , 孙嘉珺 , 张天宇 , 等 . 基于改进生成对抗网络的玻璃绝缘子自爆缺陷检测方法 [J ] . 高电压技术 , 2022 , 48 ( 3 ): 1096 - 1103 .

WANG Daolei , SUN Jiajun , ZHANG Tianyu , et al . Self-explosion defect detection method of glass insulator based on improved generative adversarial network [J ] . High Voltage Engineering , 2022 , 48 ( 3 ): 1096 - 1103 .

崔昊杨 , 韩奕 , 张驯 , 等 . 基于改进U-Net结构生成对抗网络的运动模糊绝缘子图像复原方法 [J ] . 电网技术 , 2023 , 47 ( 6 ): 2594 - 2603 .

CUI Haoyang , HAN Yi , ZHANG Xun , et al . Motion blurred insulator image restoration method based on improved U-Net structure generative adversarial network [J ] . Power System Technology , 2023 , 47 ( 6 ): 2594 - 2603 .

郝帅 , 马瑞泽 , 赵新生 , 等 . 基于超分辨深度残差网络的玻璃绝缘子自爆故障检测算法 [J ] . 高电压技术 , 2022 , 48 ( 5 ): 1817 - 1825 .

HAO Shuai , MA Ruize , ZHAO Xinsheng , et al . Self-explosion fault detection algorithm for glass insulator based on super-resolution deep residual network [J ] . High Voltage Engineering , 2022 , 48 ( 5 ): 1817 - 1825 .

卢明 , 高超 , 吴焱松 , 等 . 复合绝缘子脆性断裂与酥朽断裂差异性研究 [J ] . 高压电器 , 2022 , 58 ( 6 ): 17 - 23 .

LU Ming , GAO Chao , WU Yansong , et al . Study on difference between brittle fracture and decay-like fracture of composite insulator [J ] . High Voltage Apparatus , 2022 , 58 ( 6 ): 17 - 23 .

刘开培 , 李博强 , 秦亮 , 等 . 深度学习目标检测算法在架空输电线路绝缘子缺陷检测中的应用研究综述 [J ] . 高电压技术 , 2023 , 49 ( 9 ): 3584 - 3595 .

LIU Kaipei , LI Boqiang , QIN Liang , et al . Review of application research of deep learning object detection algorithms in insulator defect detection of overhead transmission lines [J ] . High Voltage Engineering , 2023 , 49 ( 9 ): 3584 - 3595 .

王晓杰 , 许军 , 林朝晖 , 等 . 输电线路复合绝缘子温升现象及其成因分析 [J ] . 电瓷避雷器 , 2022 ( 5 ): 165 - 171 .

WANG Xiaojie , XU Jun , LIN Chaohui , et al . Analysis of the temperature rising of composite insulators of transmission lines [J ] . Insulators and Surge Arresters , 2022 ( 5 ): 165 - 171 .

刘立帅 , 郭晨鋆 , 王黎明 , 等 . 基于频域热特征成像的复合绝缘子缺陷检测方法 [J ] . 中国电机工程学报 , 2019 , 39 ( 8 ): 2498 - 2505 .

LIU Lishuai , GUO Chenyun , WANG Liming , et al . Defects detection method for composite insulators based on frequency thermal characteristics imaging [J ] . Proceedings of the CSEE , 2019 , 39 ( 8 ): 2498 - 2505 .

谭宇璇 , 樊绍胜 . 基于图像增强与深度学习的变电设备红外热像识别方法 [J ] . 中国电机工程学报 , 2021 , 41 ( 23 ): 7990 - 7997 .

TAN Yuxuan , FAN Shaosheng . Infrared thermal image recognition of substation equipment based on image enhancement and deep learning [J ] . Proceedings of the CSEE , 2021 , 41 ( 23 ): 7990 - 7997 .

裴少通 , 马子儒 , 刘云鹏 , 等 . 500 kV输电线路劣化瓷绝缘子非线性发热特性的红外分析 [J ] . 高压电器 , 2024 , 60 ( 1 ): 33 - 40 .

PEI Shaotong , MA Ziru , LIU Yunpeng , et al . Infrared analysis of nonlinear heating characteristics of deteriorated porcelain insulator of 500 kV transmission lines [J ] . High Voltage Apparatus , 2024 , 60 ( 1 ): 33 - 40 .

ASHIKAGA H , ESTNER H L , HERZKA D A , et al . Quantitative assessment of single-image super-resolution in myocardial scar imaging [J ] . IEEE Journal of Translational Engineering in Health and Medicine , 2014 ( 2 ): 1 - 12 .

LEI Sen , SHI Zhenwei , ZOU Zhengxia . Super-Resolution for remote sensing images via local-global combined network [J ] . IEEE Geoscience and Remote Sensing Letters , 2017 , 14 ( 8 ): 1243 - 1247 .

DE FARIAS E C , DI NOIA C , HAN C H , et al . Impact of GAN-based lesion-focused medical image super-resolution on the robustness of radiomic features [J ] . Scientific Reports , 2021 , 11 ( 1 ): 1 - 12 .

唐艳秋 , 潘泓 , 朱亚平 , 等 . 图像超分辨率重建研究综述 [J ] . 电子学报 , 2020 , 48 ( 7 ): 1407 - 1420 .

TANG Yanqiu , PAN Hong , ZHU Yaping , et al . A survey of image super-resolution Reconstruction [J ] . Acta Electronica Sinica , 2020 , 48 ( 7 ): 1407 - 1420 .

杨悦 , 谢辛 , 何蕾 , 等 . 连分式插值结合卷积神经网络的超分辨率重建 [J ] . 合肥工业大学学报(自然科学版) , 2021 , 44 ( 8 ): 1146 - 1152 .

YANG Yue , XIE Xin , HE Lei , et al . Super-resolution Reconstruction using deep convolutional neural network combined with continued fraction interpolation [J ] . Journal of Hefei University of Technology (Natural Science) , 2021 , 44 ( 8 ): 1146 - 1152 .

刘云峰 , 赵洪山 , 杨晋彪 , 等 . 基于GNR先验的电力设备热成像超分辨率方法 [J ] . 红外技术 , 2023 , 45 ( 1 ): 40 - 48 .

LIU Yunfeng , ZHAO Hongshan , YANG Jinbiao , et al . Super resolution method for power equipment infrared imaging based on gradient norm-ratio prior [J ] . Infrared Technology , 2023 , 45 ( 1 ): 40 - 48 .

李方彪 , 何昕 , 魏仲慧 , 等 . 生成式对抗神经网络的多帧红外图像超分辨率重建 [J ] . 红外与激光工程 , 2018 , 47 ( 2 ): 17 - 24 .

LI Fangbiao , HE Xin , WEI Zhonghui , et al . Multiframe infrared image super-resolution Reconstruction using generative adversarial networks [J ] . Infrared and Laser Engineering , 2018 , 47 ( 2 ): 17 - 24 .

DONG Chao , LOY C C , HE Kaiming , et al . Image Super-Resolution using deep convolutional networks [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2016 , 38 ( 2 ): 295 - 307 .

DONG Chao , LOY C C , TANG Xiao'ou . Accelerating the super-resolution convolutional neural network [C ] // European Conference on Computer Vision . Springer, Cham : Springer International Publishing , 2016 : 391 - 407 .

KIM J , LEE J K , LEE K M . Accurate image Super-Resolution using very deep convolutional networks [C ] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . [S.l.] : IEEE , 2016 : 1646 - 1654 .

LEDIG C , THEIS L , HUSZÁR F , et al . Photo-Realistic single image Super-Resolution using a generative adversarial network [C ] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . [S.l.] : IEEE , 2017 : 105 - 114 .

赵洪山 , 彭轶灏 , 刘秉聪 , 等 . 基于边缘注意力生成对抗网络的电力设备热成像超分辨率重建 [J ] . 中国电机工程学报 , 2022 , 42 ( 10 ): 3564 - 3572 .

ZHAO Hongshan , PENG Yihao , LIU Bingcong , et al . Super-resolution Reconstruction of electric equipment's thermal imaging based on generative adversarial network with edge-attention [J ] . Proceedings of the CSEE , 2022 , 42 ( 10 ): 3564 - 3572 .

刘志坚 , 陶韵旭 , 刘航 , 等 . 融合残差密集与生成对抗网络的红外巡检图像超分辨率重建 [J ] . 昆明理工大学学报(自然科学版) , 2023 , 48 ( 5 ): 120 - 129 .

LIU Zhijian , TAO Yunxu , LIU Hang , et al . Super-resolution reconstruction of infrared inspection images by integrating residual dense and generative adversarial networks [J ] . Journal of Kunming University of Science and Technology (Natural Science Edition) , 2023 , 48 ( 5 ): 120 - 129 .

韩龙 , 刘凯雷 , 左超 , 等 . 改进ESRGAN的电力设备红外图像超分辨率重建方法 [J ] . 黑龙江科技大学学报 , 2023 , 33 ( 3 ): 445 - 450 .

HAN Long , LIU Kailei , ZUO Chao , et al . Super-resolution Reconstruction method for infrared images of power equipment with improved ESRGAN [J ] . Journal of Heilongjiang University of Science and Technology , 2023 , 33 ( 3 ): 445 - 450 .

ARJOVSKY M , CHINTALA S , BOTTOU L . Wasserstein generative adversarial networks [C ] // Proceedings of the 34th International Conference on Machine Learning . [S.l.] : [s.l. ] , 2017 : 214 - 223 .

GOODFELLOW I , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial networks [J ] . Communications of the ACM , 2020 , 63 ( 11 ): 139 - 144 .

CHOLLET F . Xception: Deep learning with depthwise separable convolutions [C ] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . [S.l.] : IEEE , 2017 : 1800 - 1807 .

GUO Menghao , XU Tianxing , LIU Jiangjiang , et al . Attention mechanisms in computer vision: A survey [J ] . Computational Visual Media , 2022 , 8 ( 3 ): 331 - 368 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [J ] . Proceedings of the 31st International Conference on Neural Information Processing Systems , 2017 ( 1 ): 6000 - 6010 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于改进YOLOv7的多尺度特征提取绝缘子缺陷检测算法

基于GE-YOLO算法的输电线路绝缘子多类型缺陷检测研究

可分离连接器引发的典型故障分析

基于改进YOLOv5算法的绝缘子多缺陷检测

基于带电颗粒动态积污的绝缘子电场分布研究