[1]刘正庭,尹骏刚,李凯迪,等.基于分水岭算法的绝缘子串红外图像分割方法[J].电瓷避雷器,2020,(02):216-221,228.[doi:10.16188/j.isa.1003-8337.2020.02.034]
 LIU Zhengting,YIN Jungang,LI Kaidi,et al.Infrared Image Segmentation of Insulator Strings Based on Watershed Algorithm[J].,2020,(02):216-221,228.[doi:10.16188/j.isa.1003-8337.2020.02.034]
点击复制

基于分水岭算法的绝缘子串红外图像分割方法()
分享到:

《电瓷避雷器》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2020年02期
页码:
216-221,228
栏目:
绝缘子
出版日期:
2020-04-25

文章信息/Info

Title:
Infrared Image Segmentation of Insulator Strings Based on Watershed Algorithm
作者:
刘正庭1 尹骏刚1 李凯迪1 汪宵飞2 王 欣1 万 勋2 姚建刚1
(1.湖南大学电气与信息工程学院,长沙410082; 2.国网湖南省电力科学研究院,长沙 410007)
Author(s):
LIU Zhengting1 YIN Jungang1 LI Kaidi1 WANG Xiaofei1 WANG Xin1 WAN Xun1 YAO Jiangang2
(1.College of Electrical and Information Engineering, Hunan University, Changsha 410082, China; 2.SGCC Hunan Electric Power Research Institute, Changsha 410007, China)
关键词:
瓷质绝缘子 红外图像分割 分水岭算法 泛洪算法 霍夫变换
Keywords:
Ceramic insulator infrared image segment watershed algorithm flood fill algorithm Hough transformation
DOI:
10.16188/j.isa.1003-8337.2020.02.034
摘要:
为解决500 kV瓷绝缘子串红外图像分割问题,提出了一种基于分水岭算法的图像分割方法。通过调整红外图像G分量消除云雾干扰,图像预处理后采用灰度拉伸法进行图像增强; 然后利用Otsu算法将灰度图像二值化,通过Hough变换确定绝缘子串基准线,并据此使用Floodfill算法提取绝缘子串目标区域; 角度校正后做欧式距离变换,以局部最小值为标记符避免过分割,再采用分水岭算法进行绝缘子片分割。据此对湖南省某座500 kV变电站700张红外图像进行分析,结果表明,本文所提方法具有良好的自适应性和实用性,可显著提高绝缘子红外图像智能分割准确率。
Abstract:
A new segmentation method based on watershed algorithm is proposed for the infrared image of 500 kV insulator strings. The interference of cloud and fog is eliminated by adjusting the G component of the infrared image, and the image quality is enhanced by gray processing, median filtering and gray scale stretching method. The gray image is segmented to binary image based on Otsu threshold. The baseline of an insulator string is found by Hough transformation, which is based on the Flood Fill algorithm to extract the insulator string target area. After correcting angle of insulator string, the Euclidean distance transformation is done. The local minimum value is used as a marker to avoid over segmentation. Based on the Watershed algorithm, insulators area is extracted. 700 infrared images of a 500 kV substation were analyzed for validation. The results show that the proposed method is adaptive and practical, and it can significantly improve the accuracy of intelligent segmentation of insulator strings.

参考文献/References:

[1] 张志劲,张东东,袁超,等.污秽成分对XP-160绝缘子串交流闪络特性的影响[J].高电压技术,2014, 40(7):1970-1976.ZHANG Zhijin, ZHANG Dongdong, YUAN Chao, et al. Effect of contamination component on AC flashover performance of insulator string XP-160[J]. High Voltage Engineering, 2014, 40(7): 1970-1976.
[2]国家能源局.DL/T 664—2008带电设备红外诊断技术应用导则[S].北京:中国电力出版社,2008. National Energy Administration. Application rules of infrared diagnosis for DL/T 664—2008 live electrical equipment[S]. Beijing: China electric power press, 2008.
[3]B, Subba, Reddy, et al. Study of temperature distribution along an artificially polluted insulator string[J]. Plasma Science & Technology, 2003, 5(2): 1715-1720.
[4]魏远航,陈润华.高压输电线路复合绝缘子发热机理的研究[J].高电压技术,2007(5):25-28.WEI Yuanhang, CHEN Runhua. Research on abnormal heat of composite insulator in high voltage transmission power line[J]. High Voltage Engineering, 2007(5): 25-28.
[5]胡世征.劣化绝缘子的发热机理及热象特征[J].电网技术,1997, 21(10):44-46.HU Shizheng. Heating mechanism and thermograph of degraded insulators[J]. Power System Technology, 1997, 21(10): 44-46.
[6]夏德分.红外热像检测零值绝缘子影响因素研究[D].长沙:湖南大学,2012.
[7]李唐兵,付鹏,朱向前,等.绝缘子串红外图像中绝缘子盘面和钢帽区域的自动提取方法[J].红外技术,2014, 36(8):644-648.LI Tangbing, FU Peng, ZHU Xiangqian, et al. Algorithm research on automatically extracting the disks and steel caps area of insulator from infrared image of an insulator string[J]. Infrared Technology, 2014, 36(8): 644-648.
[8]胡淋波,姚建刚,孔维辉,等.基于红外图像的高压绝缘子串自动定位方法[J].红外技术,2015, 37(12):1047-1051.HU Linbo, YAO Jiangang, KONG Weihui, et al. High voltage insulator string automatic location method based on infrared image[J]. Infrared Technology, 2015, 37(12): 1047-1051.
[9]付强,姚建刚,李唐兵,等.基于红外图像的绝缘子串钢帽和盘面区域自动提取方法[J].红外技术,2016, 38(11):969-974.FU Qiang, YAO Jiangang, LI Tangbing, et al. The automatic extraction method of the insulator string's steel caps and disks area based on infrared image[J]. Infrared Technology, 2016, 38(11): 969-974.
[10]OTSU N. A threshold selection method from gray-level histograms[J]. Systems, Man and Cybernetics, IEEE Transactions on, 1979, 9(1): 62-66.
[11]RICHARD O D, PETER E H. Use of the hough transformation to detect lines and curves in pictures[J]. Graphics and Image Processing, 1972, 15(1): 11-15.
[12]金立军,姚春羽,闫书佳,等.基于航拍图像的输电线路异物识别[J].同济大学学报:自然科学版,2013, 41(2):277-281.JIN Lijun, YAO Chunyu, YAN Shujia, et al. Recognition of extra matters on transmission lines based on aerial images[J]. Journal of Tongji University(Natural Science), 2013, 41(2): 277-281.
[13]王树文,闫成新,张天序,等.数学形态学在图像处理中的应用[J].计算机工程与应用,2004, 40(32):89-92.WANG Shuwen, YAN Chengxin, ZHANGTianxu, et al. Application of mathematical morphology in image processing[J]. Computer Engineering and Applications, 2004, 40(32): 89-92.
[14]刘岳,王小鹏,王金全,等.基于形态学重建和梯度分层修正的分水岭脑肿瘤分割[J].计算机应用研究,2015, 32(8):2487-2491.LIU Yue, WANG Xiaopeng, WANG Jinquan, et al. Watershed algorithm for brain tumor segmentation based on morphological reconstruction and gradient layered modification[J]. Application Research of Computers, 2015, 32(8): 2487-2491.
[15]BREU H, GIL J, KIRKPATRICK D, et al. Linear time euclidean distance transform algorithms[J]. IEEE Trans on Pattern Analysis&Machine Intelligence, 2002, 17(5): 529-533.
[16] PADLIA M, SHARMA J. Brain tumor segmentation from MRI using fractional sobel mask and watershed transform[C]//Information, Communication, Instrumentation and Control(ICICIC), 2017 International Conference on. IEEE, 2017: 1-6.
[17]孙惠杰,邓廷权,李艳超.改进的分水岭图像分割算法[J].哈尔滨工程大学学报,2014, 35(7):857-864.SUN Huijie, DENG Tingquan, LI Yanchao. Image segmentation algorithm based on the improved watershed algorithm[J]. Journal of Harbin Engineering University, 2014, 35(7): 857-864.
[18]黄军凯,曾华荣,杨佳鹏,等.红外热像技术在低零值绝缘子检测中的应用[J].电瓷避雷器,2013(2):40-44.HUANG Junkai, ZENG Huarong, YANG Jiapeng, et al. Application of infrared thermal imaging technology in low zero insulator detection[J]. Insulators and Surge Arresters, 2013(2): 40-44.
[19]姚建刚,付鹏,李唐兵,等.基于红外图像的绝缘子串自动提取和状态识别[J].湖南大学学报:自然科学版,2015, 42(2):74-80.YAO Jiangang, FU Peng, LI Tangbing, et al. Algorithm research of automatically extracting the area of insulator from infra-red image and state identification[J]. Journal of Hunan University Natural Sciences, 2015, 42(2): 74-80.
[20]金光熙,权光日,郎成,等.故障绝缘子的发热机理及其红外热像检测[J].电瓷避雷器,2011(5):12-15.JIN Guangxi, QUAN Guangri, LANG Cheng, et al. Heating mechanism and infrared thermography detection of failure insulators[J]. Insulators and Surge Arresters, 2011(5): 12-15.

备注/Memo

备注/Memo:
收稿日期:2018-07-05作者简介:刘正庭(1994—),男,硕士,主要研究方向:图像处理、电力设备智能检测技术等。基金资助项目:国网湖南省电力公司科研基金(编号:5216A517000T)。
更新日期/Last Update: 2020-04-25