Infrared Target Detection of High Voltage Insulation Bushing Based on Textural Features
-
摘要: 在基于传统图像分割法的红外图像目标检测中,当背景颜色和被检测物体颜色相近时,往往难以有效地识别红外图像中的被检测物。所以为了进一步提高绝缘套管在红外图像中的识别精度,文中提出一种基于绝缘套管伞裙纹理特征的目标检测方法。首先为增强图像纹理特性,将双边滤波代替传统高斯-拉普拉斯算子中的高斯卷积滤波,通过双边-拉普拉斯进行图像滤波和增强。之后针对高压绝缘套管外层伞裙的特殊纹理,建立反映伞裙周期性分布的描述子,并通过图像扫描法进行粗识别。最终基于DBSCAN(Density-Based Spatial Clustering of Applications with Noise)聚类算法,建立其超参数求解方法,实现离群点剔除和特征聚类,完成高压绝缘套管的精细分割。通过实验对比其他绝缘套管红外图像的识别算法,文中算法可以有效地精细分割出绝缘套管主体,克服其他图像分割方法的不足。并在数据集上识别率达到85%以上。Abstract: In infrared image target detection based on the traditional image segmentation method, when the background color and the color of the detected object are similar, it is often difficult to identify the detected object effectively in the infrared image. Therefore, to further improve the recognition accuracy of insulating bushings in infrared images, this paper proposes a target detection method based on the texture features of insulation bushings. First, to enhance the texture of the image, bilateral filtering is used to replace the Gaussian convolution filtering in the traditional Laplacian of Gaussian, and image filtering and enhancement are performed through Laplace of bilateral filtering. Then, based on the special texture of the outer sheds and insulation bushing, a descriptor reflecting the periodic distribution of sheds was established and rough identification was performed using the image scanning method. Finally, based on the DBSCAN clustering algorithm, a method for solving its hyper parameters was established to achieve outlier elimination and feature clustering, and to complete the fine identification of the high-voltage insulation bushing. By experimentally comparing other recognition algorithms for infrared images of insulating bushings, the algorithm in this study can effectively segment the insulation bushing main body and overcome the shortcomings of traditional image segmentation methods. The recognition rate on the dataset reached over 85%.
-
Key words:
- high voltage insulation bushing /
- infrared image /
- periodic texture /
- target detection
-
表 1 红外图像采集设备介绍
Table 1. Introduction of infrared image acquisition equipment
Parameter Value Parameter Value Acquisition equipment FLIR T600 Measurement accuracy ±2℃ Wavelength 7-13 μm Resolution 240×320 Temperature range -40℃-130℃ Measuring distance 12-15 m -
[1] 徐肖伟, 廖维, 王科, 等. 基于Havriliak-Negami介电模型的油浸式套管受潮状态评估[J]. 电测与仪表, 2018, 55(1): 53-59. doi: 10.3969/j.issn.1001-1390.2018.01.009XU Xiaowei, LIAO Wei, WANG Ke, et al. Moisture assessment of oil-impregnated bushing based on Havriliak-Negami dielectric relaxation model[J]. Electrical Measurement & Instrumentation, 2018, 55(1): 53-59. doi: 10.3969/j.issn.1001-1390.2018.01.009 [2] 杨武, 王小华, 荣命哲, 等. 基于红外测温技术的高压电力设备温度在线监测传感器的研究[J]. 中国电机工程学报, 2002(9): 114-118. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDC200209023.htmYANG Wu, WANG Xiaohua, RONG Mingzhe, et al. On-line temperature measurements with infrared technology on high voltage device[J]. Proceedings of the CSEE, 2002(9): 114-118. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDC200209023.htm [3] 刘齐, 王茂军, 高强, 等. 基于红外成像技术的电气设备故障检测[J]. 电测与仪表, 2019, 56(10): 122-126, 152. https://www.cnki.com.cn/Article/CJFDTOTAL-DCYQ201910020.htmLIU Qi, WANG Maojun, GAO Qiang, et al. Fault detection of electrical equipment based on infrared imaging technology[J]. Electrical Measurement & Instrumentation, 2019, 56(10): 122-126, 152. https://www.cnki.com.cn/Article/CJFDTOTAL-DCYQ201910020.htm [4] 马承志, 王宇雷, 杨玺, 等. 用于变电站自主巡视机器人的图像传输系统研究[J]. 电力系统保护与控制, 2014, 42(18): 105-109. doi: 10.7667/j.issn.1674-3415.2014.18.018MA Chengzhi, WANG Yulei, YANG Xi, et al. Research on image transmission system for substation autonomous patrol robot[J]. Power System Protection and Control, 2014, 42(18): 105-109. doi: 10.7667/j.issn.1674-3415.2014.18.018 [5] 黄山, 吴振升, 任志刚, 等. 电力智能巡检机器人研究综述[J]. 电测与仪表, 2020, 57(2): 26-38. https://www.cnki.com.cn/Article/CJFDTOTAL-DCYQ202002005.htmHUANG Shan, WU Zhensheng, REN Zhigang, et al. Review of electric power intelligent inspection robot[J]. Electrical Measurement & Instrumentation, 2020, 57(2): 26-38. https://www.cnki.com.cn/Article/CJFDTOTAL-DCYQ202002005.htm [6] 赵振兵, 金思新, 刘亚春. 基于NSCT的航拍绝缘子图像边缘提取方法[J]. 仪器仪表学报, 2012, 33(9): 2045-2052. doi: 10.3969/j.issn.0254-3087.2012.09.018ZHAO Zhenbing, JIN Sixin, LIU Yachun. Aerial insulator image edge extraction method based on NSCT[J]. Chinese Journal of Scientific Instrument, 2012, 33(9): 2045-2052. doi: 10.3969/j.issn.0254-3087.2012.09.018 [7] 姚晓通, 刘力, 李致远. 基于Canny边缘特征点的接触网绝缘子识别方法[J]. 电瓷避雷器, 2020(1): 142-148. https://www.cnki.com.cn/Article/CJFDTOTAL-DCPQ202001024.htmYAO Xiaotong, LIU Li, LI Zhiyuan. Identification Method of Catenary Insulator Based on Canny Edge Feature Point[J]. Insulators and Surge Arresters, 2020(1): 142-148. https://www.cnki.com.cn/Article/CJFDTOTAL-DCPQ202001024.htm [8] 刘洋, 陆倚鹏, 高嵩, 等. 边缘检测在盘形悬式瓷绝缘子串红外图像上的应用[J]. 电瓷避雷器, 2020(1): 198-203. https://www.cnki.com.cn/Article/CJFDTOTAL-DCPQ202001033.htmLIU Yang, LU Yipeng, GAO Song, et al. Edge Detection on Infrared Image of High Voltage Porcelain Disc Type Suspension Insulator Strings[J]. Insulators and Surge Arresters, 2020(1): 198-203. https://www.cnki.com.cn/Article/CJFDTOTAL-DCPQ202001033.htm [9] 方挺, 董冲, 胡兴柳, 等. 航拍图像中绝缘子串的轮廓提取和故障检测[J]. 上海交通大学学报, 2013, 47(12): 1818-1822. https://www.cnki.com.cn/Article/CJFDTOTAL-SHJT201312002.htmFANG Ting, DONG Chong, HU Xingliu, et al. Contour extraction and fault detection of insulator strings in aerial images[J]. Journal of Shanghai Jiaotong University, 2013, 47(12): 1818-1822. https://www.cnki.com.cn/Article/CJFDTOTAL-SHJT201312002.htm [10] 杨政勃, 金立军, 张文豪, 等. 基于红外图像识别的输电线路故障诊断[J]. 现代电力, 2012, 29(2): 76-79. https://www.cnki.com.cn/Article/CJFDTOTAL-XDDL201202018.htmYANG Zhenbo, JIN Lijun, ZHANG Wenhao, et al. The Fault Diagnosis of Transmission Line Based on the Infrared Image Recognition[J]. Modern Electric Power, 2019, 29(2): 76-79. https://www.cnki.com.cn/Article/CJFDTOTAL-XDDL201202018.htm [11] SHI J Y, LIU J. Mentation based on modified region growing algorithm[J]. Optical Technique, 2017, 43(4): 381-384. http://en.cnki.com.cn/Article_en/CJFDTOTAL-GXJS201704019.htm [12] 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. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDC201506006.htmCUI Juyong, CAO Yundong, WANG Wenjie. Application of an Improved Algorithm Based on Watershed Combined With Krawtchouk Invariant Moment in Inspection Image Processing of Substations[J]. Proceedings of the CSEE, 2015, 35(6): 1329-1335. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDC201506006.htm [13] 王媛彬, 尹阳. 基于红外弱目标提取的绝缘设备故障检测研究[J]. 红外技术, 2018, 40(2): 193-199. http://hwjs.nvir.cn/article/id/hwjs201802016WANG Yuanbin, YIN Yang. Research on the Insulation Equipment Fault Detection Based on Infrared Weak Target Extraction[J]. Infrared Technology, 2018, 40(2): 193-199. http://hwjs.nvir.cn/article/id/hwjs201802016 [14] 刘元宁, 刘帅, 朱晓冬, 等. 基于高斯拉普拉斯算子与自适应优化伽柏滤波的虹膜识别[J]. 吉林大学学报: 工学版, 2018, 48(5): 1606-1613. https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201805038.htmLIU Yuanning, LIU Shuai, ZHU Xiaodong, et al. LOG operator and adaptive optimization Gabor filtering for iris recognition[J]. Journal of Jilin University: Engineering and Technology Edition, 2018, 48(5): 1606-1613. https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201805038.htm [15] 曾雅琼, 陈钱. 基于改进的双边滤波的单帧红外弱小目标背景抑制[J]. 红外技术, 2011, 33(9): 537-540. doi: 10.3969/j.issn.1001-8891.2011.09.011CENG Yaqiong, CHENG Qian. Dim and Small Target Background Suppression Based on Improved Bilateral Filtering for Single Infrared Image[J]. Infrared Technology, 2011, 33(9): 537-540. doi: 10.3969/j.issn.1001-8891.2011.09.011 [16] CASSISI C, FERRO A, GIUGNO R, et al. Enhancing density-based clustering: Parameter reduction and outlier detection[J]. Information Systems, 2013, 38(3): 317-330. http://www.sciencedirect.com/science/article/pii/S0306437912001238 [17] KUMAR K M, REDDY A R M. A fast DBSCAN clustering algorithm by accelerating neighbor searching using Groups method[J]. Pattern Recognition, 2016, 58: 39-48. http://www.sciencedirect.com/science/article/pii/S0031320316001035 [18] 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, 2018, 35(6): 1329-1335. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDC201506006.htmCUI Juyong, CAO Yundong, WANG Wenjie. Application of an Improved Algorithm Based on Watershed Combined With Krawtchouk Invariant Moment in Inspection Image Processing of Substations[J]. Proceedings of the CSEE, 2018, 35(6): 1329-1335. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDC201506006.htm [19] 吕欣欣. 红外图像分割算法研究及其在电气设备故障诊断中的应用[D]. 天津: 天津理工大学, 2019.LV Xinxin. Research on Infrared Image Segmentation Algorithm and its Application in the Fault Diagnosis of Electrical Equipment[D]. Tianjin: Tianjin University of Technology, 2019.