E-FCNN Based Electric Power Inspection Image Enhancement

doi:10.11930/j.issn.1004-9649.202004144

Abstract

Abstract: For UAV patrol of transmission lines and robot inspection of unattended substations, low image resolution is one of the main problems due to long shooting distance or machine shaking. In order to solve this problem, we propose an edge-aware feedback convolutional neural network (E-FCNN), which not only adds Resnet blocks and feedback mechanism to the conventional super-resolution network to strengthen the ability of feature extraction, but also adds texture information to the edge-aware branch to enhance the image detail. Extensive experiments show that the proposed algorithm is superior to other existing algorithms, both in subjective visual quality and objective evaluation indexes such as peak signal-to-noise ratio. Practically, the proposed algorithm can improve the accuracy of insulator detection in UAV transmission line inspection.

Key words: electric power inspection, super-resolution, image enhancement, convolutional neural network, edge aware

BAI Wanrong, ZHANG Xun, ZHU Xiaoqin, LIU Jixiang, CHENG Qiyu, ZHAO Yan, SHAO Jie. E-FCNN Based Electric Power Inspection Image Enhancement[J]. Electric Power, 2021, 54(5): 179-185.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.202004144

https://www.electricpower.com.cn/EN/Y2021/V54/I5/179

References

[1] 仝卫国, 苑津莎, 李宝树. 图像处理技术在直升机巡检输电线路中的应用综述[J]. 电网技术, 2010, 34(12): 204-208
TONG Weiguo, YUAN Jinsha, LI Baoshu. Application of image processing in patrol inspection of overhead transmission line by helicopter[J]. Power System Technology, 2010, 34(12): 204-208
[2] 李道明. 可配置变电站室内图像巡检系统及关键算法研究[D]. 杭州: 浙江大学, 2019.
Li Daoming, Research on configurable image processing system for interior substation inspection and the key algorithms[D]. Hangzhou: Zhejiang University, 2019.
[3] 魏立明, 杨天野. 基于图像增强和边缘检测的电力设备故障诊断研究[J]. 吉林建筑工程学院学报, 2012, 29(4): 84-86
WEI Liming, YANG Tianye. Research on fault diagnosis of electrical equipment based on image enhancement and edge detection[J]. Journal of Jilin Institute of Architecture & Civil Engineering, 2012, 29(4): 84-86
[4] 孙宁宁, 张建国. 超分辨率重建技术在电力监控系统中的应用[C]//2011年中国电机工程学会年会, 2011.
SUN Ningning, ZHANG Jianguo. Power monitoring system based on super-resolution reconstruction[C]//2011 Annual Meeting of Chinese Society of Electrical Engineering, 2011.
[5] 赵雨田, 都洪基. 电力线数字灰度图像增强算法[J]. 计算机系统应用, 2017, 26(2): 104-111
ZHAO Yutian, DU Hongji. Gray image enhancement algorithm of power line[J]. Computer Systems & Applications, 2017, 26(2): 104-111
[6] 薛璐妍, 王红. CLAHE融合小波去噪的电力图像增强算法[J]. 数据通信, 2018(6): 31-33
XUE Luyan, WANG Hong. The algorithm for electric equipment image enhancement based on CLAHE fusion wavelet denoising[J]. Data Communications, 2018(6): 31-33
[7] 林国强, 王博, 孔英会, 等. 基于压缩感知的变电站巡检图像超分辨率重建[C]//第37届中国控制会议论文集. 武汉, 2018: 337-341.
[8] 陈智雨, 巩少岩, 俞学豪, 等. 基于自学习超分辨率的电力线路巡检可视化[J]. 电力信息与通信技术, 2019, 17(9): 11-16
CHEN Zhiyu, GONG Shaoyan, YU Xuehao, et al. Super-resolution visual patrol inspection for power line based on self-learning[J]. Electric Power Information and Communication Technology, 2019, 17(9): 11-16
[9] 王社军, 钱瑞琦, 韩周迎, 等. 浅谈基于图像增强智能变电站表盘识别方法[J]. 中国设备工程, 2019(10): 167-169
[10] 严利雄, 刘晓华, 李茗, 等. 基于生成对抗网络的红外图像电力设备超分辨算法研究[J]. 通信电源技术, 2020, 37(3): 40-43
YAN Lixiong, LIU Xiaohua, LI Ming, et al. Research on infrared images super-resolution algorithm on power equipment based on generative adversarial network[J]. Telecom Power Technology, 2020, 37(3): 40-43
[11] KRIZHEVSKY A, SUTSKEVER I, HINTON G. ImageNet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012: 1097-1105.
[12] 李文璞, 谢可, 廖逍, 等. 基于Faster RCNN变电设备红外图像缺陷识别方法[J]. 南方电网技术, 2019, 13(12): 79-84
LI Wenpu, XIE Ke, LIAO Xiao, et al. Intelligent diagnosis method of infrared image for transformer equipment based on improved faster RCNN[J]. Southern Power System Technology, 2019, 13(12): 79-84
[13] LIU B L, AIT-BOUDAOUD D. Effective image super resolution via hierarchical convolutional neural network[J]. Neurocomputing, 2020, 374: 109-116.
[14] XIE Saining, TU Zhuowen, Holistically-nested edge detection[J]. International Journal of Computer Vision, 2017, 125: 3-8.
[15] LIM Bee, SON Sanghyun, KIM Heewon, et al. Enhanced deep residual networks for single image super-resolution[C]//IEEE Computer Vision and Pattern Recognition Workshops (CVPRW), 2017.
[16] LI Zhen, YANG Jinglei, LIU Zheng, et al. Feedback network for image super-resolution[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[17] DONG Chao, CHEN Change Loy, HE Kaiming, et al. Image super-resolution using deep convolutional networks[J]. TPAMI, 2016.
[18] PELEG T, ELAD M. A statistical prediction model based on sparse representations for single image super-resolution[J]. IEEE Transactions on Image Processing, 2014, 23(6): 2569-2582.
[19] WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.
[20] REN Shaoqing, HE Kaiming, GIRSHICK R, et. al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Neural Information Processing Systems (NIPS), 2015.