基于边缘检测的瓷质绝缘子裂缝特征检测方法
|
摘要
由于人工登塔检查安全性差、电场法不能检测一些不影响电场的外绝缘缺陷等问题的存在,现有的一些绝缘子裂缝检测方法不具备实用性和通用性。为此,提出一种基于边缘检测的瓷质绝缘子裂缝特征检测方法,首先将获得的彩色绝缘子图像分解成R、G、B3个通道,并采用中值滤波去除噪声;其次采用一种改进Kirsch边缘检测算法,进行骨架提取并结合最小二乘法完成拟合,从而得到连续完整的图像边缘;然后用最大类间方差法提取得到绝缘子的裂缝区域;最后分别计算3个通道裂缝的中心坐标、长度和面积,取其平均值作为最终检测到的绝缘子裂缝特征。实验结果表明该方法提高了裂缝检测的准确性。
In view of poor safety of climbing the tower for examination by manpower,failure of the electric field method in detecting some defects of external insulation,and so on,some of current detection methods for insulator cracks are not practical and universal.Therefore,this paper presents a kind of detection method for characteristic of the porcelain insulator cracks based on edge detection which firstly decomposes the acquired color images of the insulator into three channels and uses median filter to remove noises.Secondly,by adopting a kind of improved Kirsch edge detection algorithm,this method makes skeleton extraction and finishes fitting by combining the least square method,thus getting continuous and complete image edges.Then by using the maximum inter-class method,it extracts crack areas of the insulator.Finally,the method works out center coordinates,lengths and areas of cracks of three channels and takes the average value as the characteristic of insulator crack.Experimental results indicate this method has improved accuracy in crack detection.
In view of poor safety of climbing the tower for examination by manpower,failure of the electric field method in detecting some defects of external insulation,and so on,some of current detection methods for insulator cracks are not practical and universal.Therefore,this paper presents a kind of detection method for characteristic of the porcelain insulator cracks based on edge detection which firstly decomposes the acquired color images of the insulator into three channels and uses median filter to remove noises.Secondly,by adopting a kind of improved Kirsch edge detection algorithm,this method makes skeleton extraction and finishes fitting by combining the least square method,thus getting continuous and complete image edges.Then by using the maximum inter-class method,it extracts crack areas of the insulator.Finally,the method works out center coordinates,lengths and areas of cracks of three channels and takes the average value as the characteristic of insulator crack.Experimental results indicate this method has improved accuracy in crack detection.
引文
[1]黄新波,陈贵荣,王孝敬,等.输电线路在线监测与故障诊断[M].2版.北京:中国电力出版社,2014:206-232.
[2]唐捷,俸波.一起220 kV复合绝缘子断裂故障分析[J].广东电力,2017,30(9):122-124.TANG Jie,FENG Bo.Analysis on one fracture fault of 220kV composite insulator[J].Guangdong Electric Power,2017,30(9):122-124.
[3]苏国磊,陈欢,韩玉康,等.运行20年以上500 kV输电线路绝缘子运行及抽检分析[J].广东电力,2015,28(5):103-108.SU Guolei,CHEN Huan,HAN Yukang,et al.Analysis on operation and spot check on insulators on500 kV power transmission lines running for 20 years[J].Guangdong Electric Power,2015,28(5):103-108.
[4]邱志斌,阮江军,黄道春,等.输电线路悬式瓷绝缘子老化形式分析与试验研究[J].高电压技术,2016,42(4):1259-1267.QIU Zhibin,RUAN Jiangjun,HUANG Daochun,et al.Study on aging modes and test of transmission line porcelain suspension insulators[J].High Voltage Engineering,2016,42(4):1259-1267.
[5]孙文健,刘轩东,邓桃,等.复合绝缘子芯棒典型缺陷检测方法研究现状[J].陕西电力,2016,44(10):52-56.SUN Wenjian,LIU Xuandong,DENG Tao,et al.Research on detection methods for composite insulator internal defects[J].Shaanxi Electric Power,2016,44(10):52-56.
[6]徐爱华.基于图像增强的水泥路面裂缝检测方法及应用[J].南通职业大学学报,2014,28(4):85-88.XU Aihua.Image enhancement crack detection method with application of cement pavement[J].Journal of Nantong Vocational University,2014,28(4):85-88.
[7]瞿中,林丽丹,郭阳.形态学与区域延伸相结合的图像裂缝检测算法研究[J].计算机科学,2014,41(11):297-300.QU Zhong,LIN Lidan,GUO Yang.Algorithm of image crack detection based on morphology and region extends[J].Computer Science,2014,41(11):297-300.
[8]王博.基于MATLAB图像处理的水泥路面裂缝检测研究[J].商洛学院学报,2014,28(4):42-45,74.WANG Bo.A study on cement pavement crack detection based on MATLAB image processing[J].Journal of Shangluo University,2014,28(4):42-45,74.
[9]SONKA M,HLAVAC V,BOYLE R.图像处理、分析与机器视觉[M].艾海舟,苏延超,译.北京:清华大学出版社,2011:47-51.
[10]夏清,陈亚凯,张振鑫,等.基于Laplace算子和灰色理论的热红外影像边缘检测[J].红外技术,2014,36(5):377-380,388.XIA Qing,CHEN Yakai,ZHANG Zhenxin,et al.Edge extraction algorithm of infrared thermal image based on Laplace operator and gray theory[J].Infrared Technology,2014,36(5):377-380,388.
[11]徐亮,魏锐.基于Canny算子的图像边缘检测优化算法[J].科技通报,2013,29(7):127-131,150.XU Liang,WEI Rui.An optimal algorithm of image edge detection based on Canny[J].Bulletin of Science and Technology,2013,29(7):127-131,150.
[12]郭萌,胡辽林,赵江涛.基于Kirsch和Canny算子的陶瓷碗表面缺陷检测方法[J].光学学报,2016,36(9):27-33.GUO Meng,HU Liaolin,ZHAO Jiangtao.Surface defect detection method of ceramic bowl based on Kirsch and Canny operator[J].ACTA OPTICA SINICA,2016,36(9):27-33.
[13]徐恒,彭曙蓉,毛亚珍,等.基于图像处理的输电线路覆冰厚度检测方法研究[J].陕西电力,2017,45(5):32-35.XU Heng,PENG Shurong,MAO Yazhen,et al.Transmission line ice thickness detection based on image processing[J].Shaanxi Electric Power,2017,45(5):32-35.
[14]张琳.基于Kirsch算子的图像边缘检测[D].大庆:东北石油大学,2014.
[15]张远,蒋浩,朱登明,等.基于骨架匹配的人体轮廓线提取[J].系统仿真学报,2017,29(11):2774-2781.ZHANG Yuan,JIANG Hao,ZHU Dengming,et al.Human contour extraction based on skeleton matching[J].Journal of System Simulation,2017,29(11):2774-2781.
[16]刁智华,吴贝贝,毋媛媛,等.基于图像处理的骨架提取算法的应用研究[J].计算机科学,2016,43(增刊1):232-235.DIAO Zhihua,WU Beibei,WU Yuanyuan,,et al.Application research of skeleton extraction algorithm based on image processing[J].Computer Science,2016,43(S1):232-235.
[17]章毓晋.图像工程:图像分割基础[M].2版.北京:清华大学出版社,2005:100-101.
[18]张晴晴,张云龙,齐国红.基于最大类间方差法的黄瓜病害叶片分割[J].安徽农业科学,2017,45(12):193-195,234.ZHANG Qingqing,ZHANG Yunlong,QI Guohong.Segmentation of cucumber disease leaves based on Otsu method[J].Journal of Anhui Agri.Sci.,2017,45(12):193-195,234.
[2]唐捷,俸波.一起220 kV复合绝缘子断裂故障分析[J].广东电力,2017,30(9):122-124.TANG Jie,FENG Bo.Analysis on one fracture fault of 220kV composite insulator[J].Guangdong Electric Power,2017,30(9):122-124.
[3]苏国磊,陈欢,韩玉康,等.运行20年以上500 kV输电线路绝缘子运行及抽检分析[J].广东电力,2015,28(5):103-108.SU Guolei,CHEN Huan,HAN Yukang,et al.Analysis on operation and spot check on insulators on500 kV power transmission lines running for 20 years[J].Guangdong Electric Power,2015,28(5):103-108.
[4]邱志斌,阮江军,黄道春,等.输电线路悬式瓷绝缘子老化形式分析与试验研究[J].高电压技术,2016,42(4):1259-1267.QIU Zhibin,RUAN Jiangjun,HUANG Daochun,et al.Study on aging modes and test of transmission line porcelain suspension insulators[J].High Voltage Engineering,2016,42(4):1259-1267.
[5]孙文健,刘轩东,邓桃,等.复合绝缘子芯棒典型缺陷检测方法研究现状[J].陕西电力,2016,44(10):52-56.SUN Wenjian,LIU Xuandong,DENG Tao,et al.Research on detection methods for composite insulator internal defects[J].Shaanxi Electric Power,2016,44(10):52-56.
[6]徐爱华.基于图像增强的水泥路面裂缝检测方法及应用[J].南通职业大学学报,2014,28(4):85-88.XU Aihua.Image enhancement crack detection method with application of cement pavement[J].Journal of Nantong Vocational University,2014,28(4):85-88.
[7]瞿中,林丽丹,郭阳.形态学与区域延伸相结合的图像裂缝检测算法研究[J].计算机科学,2014,41(11):297-300.QU Zhong,LIN Lidan,GUO Yang.Algorithm of image crack detection based on morphology and region extends[J].Computer Science,2014,41(11):297-300.
[8]王博.基于MATLAB图像处理的水泥路面裂缝检测研究[J].商洛学院学报,2014,28(4):42-45,74.WANG Bo.A study on cement pavement crack detection based on MATLAB image processing[J].Journal of Shangluo University,2014,28(4):42-45,74.
[9]SONKA M,HLAVAC V,BOYLE R.图像处理、分析与机器视觉[M].艾海舟,苏延超,译.北京:清华大学出版社,2011:47-51.
[10]夏清,陈亚凯,张振鑫,等.基于Laplace算子和灰色理论的热红外影像边缘检测[J].红外技术,2014,36(5):377-380,388.XIA Qing,CHEN Yakai,ZHANG Zhenxin,et al.Edge extraction algorithm of infrared thermal image based on Laplace operator and gray theory[J].Infrared Technology,2014,36(5):377-380,388.
[11]徐亮,魏锐.基于Canny算子的图像边缘检测优化算法[J].科技通报,2013,29(7):127-131,150.XU Liang,WEI Rui.An optimal algorithm of image edge detection based on Canny[J].Bulletin of Science and Technology,2013,29(7):127-131,150.
[12]郭萌,胡辽林,赵江涛.基于Kirsch和Canny算子的陶瓷碗表面缺陷检测方法[J].光学学报,2016,36(9):27-33.GUO Meng,HU Liaolin,ZHAO Jiangtao.Surface defect detection method of ceramic bowl based on Kirsch and Canny operator[J].ACTA OPTICA SINICA,2016,36(9):27-33.
[13]徐恒,彭曙蓉,毛亚珍,等.基于图像处理的输电线路覆冰厚度检测方法研究[J].陕西电力,2017,45(5):32-35.XU Heng,PENG Shurong,MAO Yazhen,et al.Transmission line ice thickness detection based on image processing[J].Shaanxi Electric Power,2017,45(5):32-35.
[14]张琳.基于Kirsch算子的图像边缘检测[D].大庆:东北石油大学,2014.
[15]张远,蒋浩,朱登明,等.基于骨架匹配的人体轮廓线提取[J].系统仿真学报,2017,29(11):2774-2781.ZHANG Yuan,JIANG Hao,ZHU Dengming,et al.Human contour extraction based on skeleton matching[J].Journal of System Simulation,2017,29(11):2774-2781.
[16]刁智华,吴贝贝,毋媛媛,等.基于图像处理的骨架提取算法的应用研究[J].计算机科学,2016,43(增刊1):232-235.DIAO Zhihua,WU Beibei,WU Yuanyuan,,et al.Application research of skeleton extraction algorithm based on image processing[J].Computer Science,2016,43(S1):232-235.
[17]章毓晋.图像工程:图像分割基础[M].2版.北京:清华大学出版社,2005:100-101.
[18]张晴晴,张云龙,齐国红.基于最大类间方差法的黄瓜病害叶片分割[J].安徽农业科学,2017,45(12):193-195,234.ZHANG Qingqing,ZHANG Yunlong,QI Guohong.Segmentation of cucumber disease leaves based on Otsu method[J].Journal of Anhui Agri.Sci.,2017,45(12):193-195,234.