|本期目录/Table of Contents|

[1]刘树吉,刘 颖,刘 为,等.基于稀疏表示的电力设备图像识别方法[J].电子设计工程,2019,27(22):162-165.
 LIU Shuji,LIU Ying,LIU Wei,et al.Electric equipment image recognition based on sparse representation[J].SAMSON,2019,27(22):162-165.
点击复制

基于稀疏表示的电力设备图像识别方法(PDF)
分享到:

《电子设计工程》[ISSN:1674-6236/CN:61-1477/TN]

卷:
27
期数:
2019年22期
页码:
162-165
栏目:
图像分析与多媒体
出版日期:
2019-11-20

文章信息/Info

Title:
Electric equipment image recognition based on sparse representation
文章编号:
1674-6236(2019)22-0162-04
作者:
刘树吉刘 颖刘 为同东辉刘雪松
(国网辽宁省电力有限公司信息通信分公司,辽宁 沈阳 110006)
Author(s):
LIU Shu?ji LIU Ying LIU Wei TONG Dong?hui LIU Xue?song
(State Grid Liaoning Electric Power Co., Ltd. Information and Communication Branch,Shenyang 110006, China)
关键词:
电力设备 图像识别 稀疏表示 贝叶斯稀疏
Keywords:
electric equipment image recognition sparse representation Bayesian compressive sensing
分类号:
TM614
DOI:
-
文献标志码:
A
摘要:
电力设备图像分析对于电力巡线、检修具有重要的实用意义。本文提出一种基于稀疏表示的电力设备图像识别方法。考虑到图像采集过程中不可避免受到光线条件、噪声干扰等因素的影响,本方法采用贝叶斯压缩感知算法求解稀疏表示问题。该算法具有较强的噪声稳健性和抗干扰能力,适用于电力设备图像面临的不同条件。实验中,对绝缘子、变压器和断路器三类电力设备的图像进行分类,提出方法的准确率达到93.56%,并且在噪声干扰条件下可以保持较强的稳健性,表明了其有效性。
Abstract:
Electric equipment image analysis has important meanings to power line inspection and repairment. This paper proposes an electric equipment image recognition method based on sparse representation. Considering the image collection is inevitably influenced by the light condition and noise corruption, this paper uses Bayesian compressive sensing algorithm to solve the sparse representation problem. The algorithm has good robustness to noises and interferences, which is suitable to handle the conditions in electrical equipment images. In the experiments, three electrical equipments, i.e., insulators, power transformers, and breakers, are classified and the accuracy reaches 93.56%. In addition, the robustness of the proposed method under noise corruption is also superior. All the results validate the effectiveness of the proposed method.

参考文献/References:

[1] 余萍,董保国.基于SIFT特征匹配的电力设备图像变化参数识别[J]. 中国电力, 2012,45(11):60-64.[2] 罗桓,田翔. 基于改进Canny算子的电力设备图像检测研究[J]. 电测与仪表, 2014,51(10):77-81.[3] 束江,崔昊杨,刘晨斐. 改进MSRCR的电力设备图像增强算法研究[J]. 物联网技术, 2017,7(10):47-50.[4] 金立军,陈俊佑,张文豪,等. 基于图像处理技术的电力设备局部放电紫外成像检测[J]. 电力系统保护与控制,2013,41(8):43-48.[5] 崔巨勇,曹云东,王文杰. 基于分水岭与Krawtchouk不变矩相结合的改进方法在变电站巡检图像处理中的应用[J]. 中国电机工程学报,2015,35(6):1329-1335.[6] 郝艳捧,蒋晓蓝,阳 林,等. 基于图像分割评估运行绝缘子自然覆冰程度[J]. 高电压技术,2017,43(7):285-292.[7] 张重远,闫 康,汪佛池,等. 基于图像特征提取与BP 经网络的绝缘子憎水性识别方法[J]. 高电压技术,2014,40(5):1446-1452.[8] Wang J J, Wang J H, Shao J W. Image recognition of icing thickness on power transmission lines based on a least squares Hough transform[J]. Energies, 2017, 10 (4): 415-430.[9] 李 俊,钟幼平,黄文娟,等. 改进的Hough 变换在覆冰厚度测量中的应用[J]. 现代电力,2014,31(3):91-94.[10]邵文泽,韦志辉. 压缩感知基本理论:回顾与展望[J]. 中国图象图形学报, 2012,17(1):4-15.[11]马坚伟,徐杰,鲍跃全,等. 压缩感知及其应用:从稀疏约束到低秩约束优化[J]. 信号处理, 2012, 28(5):609-623.[12]杨方方,吴锡生,顾标准. 基于低秩子空间投影和Gabor特征的稀疏表示人脸识别算法[J]. 计算机工程与科学, 2017,39(1):131-137.[13]王瑞,杜林峰,陈俊丽,等. 结合随机投影和稀疏表示的图像融合方法[J]. 上海交通大学学报, 2014,48(10):1421-1427.[14]张新征,黄培康.基于贝叶斯压缩感知的SAR目标识别[J].系统工程与电子技术,2013,35(1):40-44.[15]周凯,元昌安,覃晓,等. 基于核贝叶斯压缩感知的人脸识别[J]. 山东大学学报(工学版), 2016, 46(3):74-78.[16]Zhang X N. Noise-robust target recognition of SAR images based on attribute scattering center matching[J]. Remote Sensing Letters, 2019,10(2):186-194.

相似文献/References:

[1]张宏钊,黄荣辉,姚森敬,等.对嵌入式系统的电力设备紫外监测系统设计的分析[J].电子设计工程,2016,(11):112.
 ZHANG Hong-zhao,HUANG Rong-hui,YAO Sen-jing,et al.For electrical equipment uv monitoring system design of the embedded system analysis[J].SAMSON,2016,(22):112.
[2]赵宏伟,刘 波,刘 恒.一种改进的稀疏表示DOA估计算法[J].电子设计工程,2016,(09):133.
 ZHAO Hong-wei,LIU Bo,LIU Heng.An improved DOA estimation algorithm with sparse representation[J].SAMSON,2016,(22):133.
[3]黄惠迪,官洪运,邓 昶,等.基于Android平台的车道线检测系统设计[J].电子设计工程,2015,(15):99.
 HUANG Hui-di,GUAN Hong-yun,DENG Chang,et al.A method to implementation of lane detection under Android system[J].SAMSON,2015,(22):99.
[4]刘 镇,张 敏.基于HALCON与SURF的多特征融合条烟识别系统[J].电子设计工程,2015,(02):44.
 LIU Zhen,ZHANG Min.Cigarette recognition system of feature fusion based on HALCON and SURF[J].SAMSON,2015,(22):44.
[5]王 欣,沈思秋.一种改进的基于K-SVD字典的图像去噪算法[J].电子设计工程,2014,(23):189.
 WANG Xin,SHEN Si-qiu.An improved image denoising algorithm based on K-SVD dictionary[J].SAMSON,2014,(22):189.
[6]李 磊,郭俊辉.基于稀疏表示的船体检测方法研究[J].电子设计工程,2014,(21):138.
 LI Lei,GUO Jun-hui.A new method of vessel detection based on sparse representation[J].SAMSON,2014,(22):138.
[7]王化喆,李德启.第二代曲波加权改进算法在图像处理中的应用[J].电子设计工程,2014,(15):78.
 WANG Hua-zhe,LI De-qi.Application in image processing based on the second generation curvelet weighted algorithm[J].SAMSON,2014,(22):78.
[8]李 志,郑江滨. 基于稀疏表示的红外小目标跟踪[J].电子设计工程,2013,(10):178.
 LI Zhi,ZHENG Jiang-bin. Tracking infrared small targets based on sparse representation models[J].SAMSON,2013,(22):178.
[9]马 飞,申 远,孙国瑞,等.印刷体英文单词识别与朗读在辅助阅读中的应用[J].电子设计工程,2012,(03):130.
 MA Fei,SHEN Yuan,SUN Guo-rui,et al.Recognition and speech of printed-English-character to apply for reading[J].SAMSON,2012,(22):130.
[10]于 洪,杜小丹,申建军.基于微机的摄像头监控系统设计[J].电子设计工程,2011,(12):166.
 YU Hong,DU Xiaodan,SHEN Jianjun.Design of camera supervise system based on personal computer[J].SAMSON,2011,(22):166.

备注/Memo

备注/Memo:
收稿日期:2019-03-14 稿件编号:201903107作者简介:刘树吉(1970—),男,辽宁沈阳人,硕士,高级工程师。研究方向:计算机应用技术。
更新日期/Last Update: 2019-11-25