New Corona Discharge Segmentation Method for Power Line Based on Ultraviolet Image
-
摘要: 受拍摄环境及局部放电程度影响，夜间型紫外相机拍摄电晕放电图像不清晰、放电区域的颜色不仅接近背景颜色且与背景交叉重叠等导致难以自动分割局部放电，针对该问题提出一种新的电力线紫外图像局部放电区域精确分割方法。首先，构建基于Unet深度学习语义分割模型，利用已训练Unet网络对紫外图像语义分割获得电晕放电区域粗分割结果；其次，将放电区域紫外图像转换为灰度图像，基于前景加权的Otsu阈值分割法对粗分割结果进行精确分割。对426个样本进行测试，本文方法全部分割出了样本图像中的局部放电区域，且分割出的放电区域与真值之间的误差接近0，所提出的电晕放电分割方法能为局部放电大小量化和评估提供准确的数据源。Abstract: Corona discharge images collected with night-type ultraviolet cameras are affected by the photographer's environment and the degree of partial discharge, and the color of the discharge area is not only close to the background but also overlaps with the background, which makes it difficult to automatically segment corona discharge. This paper proposes a coarse-to-fine corona discharge ultraviolet (UV) image segmentation method. First, a deep-learning semantic segmentation model was constructed, and rough segmentation results of the corona discharge were obtained using a trained Unet network. Second, the UV image of the discharge region was converted into a gray image, and the rough segmentation result was accurately segmented based on the Otsu threshold segmentation method with foreground weighting. A total of 426 samples were tested, and all the corona discharge regions in the sample images were segmented using the proposed method. The error between the segmented discharge regions and the true value was close to 0. The proposed corona discharge segmentation method provides accurate data sources for the quantification and evaluation of corona discharges.
-
Keywords:
- corona discharge /
- ultraviolet imaging /
- semantic segmentation /
- Otsu threshold
-
-
![]()
图 1 “日盲”紫外图像及电晕放电分割结果
Figure 1. Solar-blind UV image and its corona discharge segmentation results
![]()
图 8 放电区域精确分割结果及比较
Figure 8. Discharge area segmentation results and comparison for different methods
![]()
图 9 不同方法对电晕放电分割结果比较：(a) 原图；(b) 放电区域真值；(c) Unet分割结果；(d) Otsu分割结果；(e) 本文分割结果
Figure 9. Comparison of corona discharge segmentation results for different methods : (a) Original images; (b) Ground-truth of Corona discharge areas; (c) Segmentation results based on Unet network; (d) Segmentation results based on Otsu method; (e) Segmentation results based on our method
表 1 全部测试图像语义分割混淆矩阵
Table 1 Semantic segmentation confusion matrix
Predict labeled True labeled TP=118884 FN=29524 FP=28980 TN=57760532 
下载: 导出CSV
表 2 部分图像分割的MCE值
Table 2 The MCE values of image segmentation
Segmentation method Sample 1 Sample 2 Sample 2 Sample 3 Unet 0.3638 0.4752 0.6675 0.5475 Otsu 0.2301 0.1394 0.2137 0.1909 Our method 0.0542 0.0338 0.0165 0.0291
下载: 导出CSV
-
[1] 王胜辉. 基于紫外成像的污秽悬式绝缘子放电检测及评估[D]. 北京: 华北电力大学, 2011. WANG Shenghui. Detection and Assessment of Contaminated Suspension Insulator Discharge Based on Ultraviolet Imaging[D]. Beijing: North China Electric Power University, 2021.
[2] 张显. 基于紫外检测技术的绝缘子电晕放电特性研究[D]. 长沙: 长沙理工大学, 2016. ZHANG Xian. Research the Characteristics of Insulator Corona Discharge based on UV Imaging Technology[D]. Changsha: Changsha University of Science & Technology, 2016.
[3] 赵太飞, 李晗辰, 张港, 等. 无人机巡线的紫外放电检测研究[J]. 电子测量与仪器学报, 2020, 34(12): 36-42. https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY202012005.htm ZHAO Taifei, LI Hanchen, ZHANG Gang, et al. Ultraviolet discharge detection research for UAV patrol[J]. Journal of Electronic Measurement and Instrumentation, 2020, 34(12): 36-42. https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY202012005.htm
[4] WANG S, LV F, LIU Y. Estimation of discharge magnitude of composite insulator surface corona discharge based on ultraviolet imaging method[J]. IEEE Transactions on Dielectrics & Electrical Insulation, 2014, 21(4): 1697-1704.
[5] ZHANG Z, WEI Z, ZHANG D, et al. Comparison of different characteristic parameters acquired by UV imager in detecting corona discharge[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2016, 23(3): 1597-1604. DOI: 10.1109/TDEI.2016.005499
[6] LIN Y, CHEN Y, ZHOU J, et al. Gray Standard deviation based ultraviolet image segmentation for electrical equipment[C]//Journal of Physics: Conference Series, 2019, 1169(1): 012051.
[7] 艾建勇, 金立军. 基于紫外图像的接触网棒瓷绝缘子污秽状态检测[J]. 电工技术学报, 2016, 31(10): 112-118. DOI: 10.3969/j.issn.1000-6753.2016.10.013 AI Jianyong, JIN Lijun. Rod porcelain insulator filth state detection of catenary based on ultraviolet image[J]. Transactions of China Electrotechnical Society, 2016, 31(10): 112-118. DOI: 10.3969/j.issn.1000-6753.2016.10.013
[8] 刘云鹏, 李泳霖, 裴少通, 等. 基于紫外成像技术的彩色光斑映射识别算法研究[J]. 华北电力大学学报: 自然科学版, 2022(4): 1-9. https://www.cnki.com.cn/Article/CJFDTOTAL-HBDL202303001.htm LIU Yunpeng, LI Yonglin, PEI Shaotong, et al. Research on color spot mapping recognition algorithm based on ultraviolet imaging technology[J]. Journal of North China Electric Power University: Nature Science, 2022(4): 1-9. https://www.cnki.com.cn/Article/CJFDTOTAL-HBDL202303001.htm
[9] 李勋, 张宏钊, 胡元潮, 等. 基于C-V模型的电晕放电紫外成像分割及特征量研究[J]. 高压电器, 2017, 53(8): 123-128. https://www.cnki.com.cn/Article/CJFDTOTAL-GYDQ201708021.htm LI Xun, ZHANG Hongzhao, HU Yuanchao, et al. Ultraviolet image segmentation and characteristic quantities of corona discharge based on C-V model[J]. High Voltage Apparatus, 2017, 53(8): 123-128. https://www.cnki.com.cn/Article/CJFDTOTAL-GYDQ201708021.htm
[10] 闵超波, 顾燕, 杨锋. 基于泊松分布的日盲紫外电晕检测[J]. 红外技术, 2020, 42(8): 715-721. http://hwjs.nvir.cn/article/id/hwjs202008002 MIN Chaobo, GU Yan, YANG Feng. Corona detection of solar-blind ultraviolet via Poisson distribution[J]. Infrared Technology, 2020, 42(8): 715-721. http://hwjs.nvir.cn/article/id/hwjs202008002
[11] 王胜辉, 董兴浩, 王玺铭, 等. 基于改进SSD算法和紫外成像的悬式绝缘子放电严重程度评估[J]. 华北电力大学学报: 自然科学版, 2022(4): 1-10. https://www.cnki.com.cn/Article/CJFDTOTAL-HBDL202305005.htm WANG Shenghui, DONG Xinghao, WANG Xuming et. al. Suspension insulator based on improved SSD algorithm and UV imaging discharge severity assessment[J]. Journal of North China Electric Power University(Nature Science), 2022(4): 1-10. https://www.cnki.com.cn/Article/CJFDTOTAL-HBDL202305005.htm
[12] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention–MICCAI, 2015: 234-241
[13] Otsu N. A threshold selection method from gray-level Histograms[J]. IEEE Transactions on Systems Man & Cybernetics, 2007, 9(1): 62-66.
[14] Kapur J, Sahoo P K, Wong A. A new method for gray-level picture thresholding using the entropy of the histogram[J]. Computer Vision, Graphics, and Image Processing, 1985, 29(3): 273-285. DOI: 10.1016/0734-189X(85)90125-2
[15] Kittler J, Illingworth J. Minimum error thresholding[J]. Pattern Recognition, 1986, 19(1): 41-47. DOI: 10.1016/0031-3203(86)90030-0
[16] XU X, XU S, JIN L, et. al. Characteristic analysis of Otsu threshold and its applications[J]. Pattern Recognition Letters, 2011, 32(7): 956-961. DOI: 10.1016/j.patrec.2011.01.021
[17] 袁小翠, 吴禄慎, 陈华伟. 基于Otsu方法的钢轨图像分割[J]. 光学精密工程, 2016, 24(7): 1772-1781. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201607028.htm YUAN Xiaocui, WU Lushen, CHEN Huawei. Rail image segmentation based on Otsu threshold method[J]. Optics and Precision Engineering, 2006, 24(7): 1772-1781. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201607028.htm
[18] 袁刚, 许志浩, 康兵, 等. 基于DeepLabv3+网络的电流互感器红外图像分割方法[J]. 红外技术, 2021, 43(11): 1127-1134. http://hwjs.nvir.cn/article/id/b9df2f53-2244-471b-b0ec-42159cfaa654 YUAN Gang, XU Zhihao, KANG Bing. Deep Labv3+ network-based infrared image segmentation method for current transformer[J]. Optics and Precision Engineering, 2021, 43(11): 1127-1134. http://hwjs.nvir.cn/article/id/b9df2f53-2244-471b-b0ec-42159cfaa654
[19] 张开放, 苏华友, 窦勇. 一种基于混淆矩阵的多分类任务准确率评估新方法[J]. 计算机工程与科学, 2021, 43(11): 1910-1919. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJK202111002.htm ZHANG Kaifang, SU Huayou, DOU Yong. A new multi-classification task accuracy evaluation method based on confusion matrix[J]. Computer Engineering & Science, 2021, 43(11): 1910-1919. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJK202111002.htm
-
期刊类型引用(19)
1. 王琦，张欣唯，童悦，王昱晴，张锦，王咏涛，袁小翠. 一种复杂背景下电气设备红外图像精确分割方法. 激光与红外. 2025(03): 399-407 . 
百度学术
2. 孙超，祁步仁，王义成，张国梁，李瑾辉. 基于物联网技术的电力设备异常温升状态监测方法. 微型电脑应用. 2025(02): 249-252+256 . 百度学术
3. 陈秋菊，彭天昊，康万杰，何国锋. 特征融合的电力机械设备过热故障红外检测. 机械设计与制造. 2024(04): 337-341 . 百度学术
4. 林颖，张峰达，李壮壮，郑文杰，戈宁. 基于大模型的红外图像电力设备交互式分割. 网络新媒体技术. 2024(02): 53-60+67 . 百度学术
5. 尤渺. 基于模糊Petri网和马尔科夫链理论的水电厂设备故障应急响应模型. 电子设计工程. 2024(10): 59-63 . 百度学术
6. 曹李伟. 基于红外热成像技术的变电设备热故障识别方法. 电工技术. 2024(09): 130-132 . 百度学术
7. 江钊. 基于深度神经网络的市政电气故障识别方法研究. 电气技术与经济. 2024(07): 48-50 . 百度学术
8. 张宇，袁小翠，许志浩，康兵. 复杂背景下断路器红外图形精确分割方法. 江西电力. 2024(03): 1-7 . 百度学术
9. 戚浩明. 风力发电厂输变电设备电连接发热故障主动预警研究. 电气时代. 2024(09): 35-39 . 百度学术
10. 李荪. 基于红外测温技术的变电设备温度异常检测研究. 电气技术与经济. 2024(10): 57-59 . 百度学术
11. 黄颖，彭铖，夏骏. 梯度扩散下的电气设备调试危险点自适应识别方法. 微型电脑应用. 2024(11): 182-185 . 百度学术
12. 张彦迪，陈江宁，老大中. 改进激光传感器的电气设备过热故障识别方法. 计算机仿真. 2023(11): 91-95 . 百度学术
13. 汤婕. 物联网环境下电气设备实时状态信息监测技术. 廊坊师范学院学报(自然科学版). 2023(04): 66-70 . 百度学术
14. 张婷婷，张冬霞，潘红娜. 基于无线网络的船舶电气设备过热监测系统. 舰船科学技术. 2023(24): 180-183 . 百度学术
15. 林颖，张峰达，李壮壮，孙艺玮，于文牮. 基于交互式分割的电力设备红外图像自动标注方法. 山东电力技术. 2023(12): 20-25+44 . 百度学术
16. 刘赫，赵天成，刘俊博，矫立新，许志浩，袁小翠. 基于深度残差UNet网络的电气设备红外图像分割方法. 红外技术. 2022(12): 1351-1357 . 本站查看
17. 梁玉真，张仕海，汝承印，朱冶诚. 海上平台电气温度监控系统及预测模型研究. 电子测量技术. 2022(22): 162-169 . 百度学术
18. 谢水斌. 智能化变电站电气设备的安装及调试. 光源与照明. 2022(10): 158-160 . 百度学术
19. 李烈熊. 基于ZigBee技术的机电设备故障智能监测系统设计. 信息与电脑(理论版). 2022(20): 140-142 . 百度学术
其他类型引用(1)
计量
- 文章访问数: 86
- HTML全文浏览量: 53
- PDF下载量: 29
- 被引次数: 20
