融合深度学习的无人机巡检绝缘子自爆检测研究

doi:10.3969/j.issn.0255-8297.2021.02.004

应用科学学报 ›› 2021, Vol. 39 ›› Issue (2): 222-231.doi: 10.3969/j.issn.0255-8297.2021.02.004

• 通信工程 • 上一篇

融合深度学习的无人机巡检绝缘子自爆检测研究

王万国^1,2, 慕世友², 刘越², 刘广秀², 郎芬玲³

1. 国网山东省电力公司电力科学研究院, 山东济南 250000;
2. 国网智能科技股份有限公司, 山东济南 250000;
3. 航天图景(北京) 科技有限公司, 北京 101300

收稿日期:2019-03-05 发布日期:2021-04-01
通信作者: 王万国,高工,研究方向为模式识别与智能系统、智能运检及无人机巡检图像智能处理与分析。E-mail:wangwanguo03@163.com E-mail:wangwanguo03@163.com
基金资助:
国网公司科技项目（No.5200-201916261A-0-0-00）资助

Research on Insulator Self Exploding Detection in UAV Inspection Based on Deep Learning

WANG Wanguo^1,2, MU Shiyou², LIU Yue², LIU Guangxiu², LANG Fenling³

1. State Grid Shandong Electric Power Research Institute, Jinan 250000, Shandong, China;
2. State Grid Intelligence Technology Co., Ltd., Jinan 250000, Shandong, China;
3. Tukrin Technology(Beijing) Co., Ltd., Beijing 101300, China

Received:2019-03-05 Published:2021-04-01

摘要/Abstract

摘要： 绝缘子自爆检测是无人机电力输电线路巡检的一项重要内容，准确、快速、自动寻找绝缘子自爆区域，能大量节省无人机巡检图像数据处理工作量，提高巡检的精度和效率。本文针对目前绝缘子自爆区域检测存在样本少、目标小且精度不高的问题，提出了一种融合深度学习的无人机巡检绝缘子自爆区域检测方法。该方法用大量绝缘子样本训练深度学习目标识别模型，在识别出绝缘子区域内利用计算机视觉方法对自爆区域进行检测。本文方法综合了深度学习检测复杂目标，以及计算机视觉无需大量样本且能够检测小目标的优点。实验表明：本文算法对缺陷的检测精度能够达到84.8%，对于绝缘子自爆检测具有积极的意义和应用价值。

关键词: 绝缘子, 绝缘子自爆, 深度学习, 目标检测

Abstract: Insulator self-exploding detection is an important part of UAV inspection. Accurate, rapid and automatic searching for insulator self-exploding areas can greatly save the workload of UAV inspection data processing and improve inspection accuracy and efficiency. Aiming at the problem of low sample size, small target and low precision in the current insulator self-exploding detection, this paper proposes a deep learning self-exploding detection method for UAV inspection insulators. The method uses a large number of collected insulator samples to train the deep learning detection model, and then uses the computer vision method to detect the self-exploding region in the detected insulator. The method of this paper synthesizes the advantages of deep learning in detecting complex targets and the fact that computer vision does not require a large number of samples and can detect small targets. Experiments show that the detection accuracy of this algorithm can reach 84.8%. It has positive significance and application value for insulator self-exploding detection.

Key words: insulator, insulator self-exploding, deep learning, object detection

中图分类号:

P237

王万国, 慕世友, 刘越, 刘广秀, 郎芬玲. 融合深度学习的无人机巡检绝缘子自爆检测研究[J]. 应用科学学报, 2021, 39(2): 222-231.

WANG Wanguo, MU Shiyou, LIU Yue, LIU Guangxiu, LANG Fenling. Research on Insulator Self Exploding Detection in UAV Inspection Based on Deep Learning[J]. Journal of Applied Sciences, 2021, 39(2): 222-231.

参考文献

[1] 陈庆, 闫斌, 叶润, 等. 航拍绝缘子卷积神经网络检测及自爆识别研究[J]. 电子测量与仪器学报, 2017(6):942-953. Chen Q, Yan B, Ye R, et al. Insulator detection and recognition of explosion fault based on convolutional neural networks[J]. Journal of Electronic Measurement and Instrumentation, 2017(6):942-953. (in Chinese)
[2] Schapire R E. The boosting approach to machine learning an overview[J]. Msri Workshop on Nonlinear Estimation & Classification, 2003(171):149-171.
[3] Viola P, Jones M. Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001 IEEE Computer Society Conference on. IEEE, 2001, 1:I-511-I-518.
[4] Dalal N, Triggs B, Schmid C. Human detection using oriented histograms of flow and appearance[C]//IEEE Conference on Computer Vision and Pattern Recognition. Hawaii, USA, 2001:511-518.
[5] Ren S, He K, Girshick R. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6):1137.
[6] Liu W, Anguelov D, Erhan D, et al. SSD:single shot multi-box detector[C]//Proceeding soft the 14th European Conference on Computer Vision. Amsterdam The Netherland, 2016:21-37.
[7] Redmon J, Divvala S, Girshick R. You only look once:unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2016:779-788.
[8] Redmon J, Farhadi A. YOLO9000:better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2016:6517-6525.
[9] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[DB/OL]. 2014[2019-03-05]. https://arxiv.org/abs/1409.1556.
[10] He K, Zhang X, Ren S. Deep residual learning for image recognition[J]. IEEE Computer Society, 2015:770-778.
[11] Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2015:1-9.
[12] 王淼, 杜毅, 张忠瑞. 无人机辅助巡视及绝缘子缺陷图像识别研究[J]. 电子测量与仪器学报, 2015(12):1862-1869. Wang M, Du Y, Zhang Z R. Study on power transmission lines inspection using unmanned aerial vehicle and image recognition of insulator defect[J]. Journal of Electronic Measurement and Instrumentation, 2015(12):1862-1869. (in Chinese)
[13] 商俊平, 李储欣, 陈亮. 基于视觉的绝缘子定位与自爆缺陷检测[J]. 电子测量与仪器学报, 2017(6):844-849. Shang J P, Li C X, Chen L. Location and detection for self-explode insulator based on vision[J]. Journal of Electronic Measurement and Instrumentation, 2017(6):844-849. (in Chinese)
[14] 张少平, 杨忠, 黄宵宁, 等. 航拍图像中玻璃绝缘子自爆缺陷的检测及定位[J]. 太赫兹科学与电子信息学报, 2013(4):609-613. Zhang S P, Yang Z, Huang X N, et al. Defects detection and positioning for glass insulator from aerial images[J]. Journal of Terahertz Science and Electronic Information Technology, 2013(4):609-613. (in Chinese)
[15] 姜浩然, 金立军, 闫书佳. 航拍图像中绝缘子的识别与故障诊断[J]. 机电工程, 2015, 32(2):274-278. Jiang H R, Jin L J, Yan S J. Recognition and fault diagnosis of insulator string in aerial images[J]. Journal of Mechanical & Electrical Engineering, 2015, 32(2):274-278. (in Chinese)
[16] 程海燕, 韩璞, 王迪, 等. 一种电网巡检航拍图像中绝缘子定位方法[J]. 系统仿真学报, 2017, 29(6):1327-1336. Cheng H Y, Han P, Wang D, et al. Location method of insulators in power grid patrol aerial images[J]. Journal of System Simulation, Journal of System Simulation, 2017, 29(6):1327-1336. (in Chinese)

融合深度学习的无人机巡检绝缘子自爆检测研究

Research on Insulator Self Exploding Detection in UAV Inspection Based on Deep Learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	张彤彤, 董军宇, 赵浩然, 李琼, 孙鑫. 基于知识蒸馏的轻量型浮游植物检测网络[J]. 应用科学学报, 2020, 38(3): 367-376.
[2]	王灿军, 廖鑫, 陈嘉欣, 秦拯, 刘绪崇. 基于卷积神经网络的面部图像修饰检测[J]. 应用科学学报, 2019, 37(5): 618-630.
[3]	朱翌明, 陈帆, 和红杰, 陈鸿佑. 基于秘密信息驱动的正交GAN信息隐藏模型[J]. 应用科学学报, 2019, 37(5): 721-732.
[4]	李芳, 钟映春, 戚剑, 罗鹏. 周围神经MicroCT图像中神经束区域的自动分离[J]. 应用科学学报, 2019, 37(3): 359-368.
[5]	冯发杰, 吏军平, 丁亚洲, 朱坤, 崔卫红. 基于多尺度视觉特征组合的高分遥感影像目标检测[J]. 应用科学学报, 2018, 36(3): 471-484.
[6]	杨滨, 张涛, 陈先意. 基于深度学习的图像局部模糊识别[J]. 应用科学学报, 2018, 36(2): 321-330.
[7]	张过. 卫星视频处理与应用进展[J]. 应用科学学报, 2016, 34(4): 361-370.
[8]	王国力，周伟，丛瑜，关键. 多尺度自卷积方差显著性SAR图像目标检测[J]. 应用科学学报, 2013, 31(6): 607-6.
[9]	蔚婧1，杨志伟2，李亚安1. 面向地面运动目标检测的SAR图像分辨率选取[J]. 应用科学学报, 2012, 30(5): 493-497.
[10]	龚清勇朱兆达. 非均匀环境下雷达动目标检测的空时自适应处理[J]. 应用科学学报, 2009, 27(4): 370-374.