Abstract The identification and location of the target with a complicated background is a very hot and difficult issue in the field of pattern recognition. In the complicated background, to identify the insulator string from aerial image used for inspection of grid, a new insulators image identification and location algorithm based on frequency-tuned is proposed. First of all, the inspection image containing the insulators is transformed from RGB color space into HSV color space, threshold segmentation is carried on H, S and V component spaces. Then, by using the low frequency and high frequency information, the significant information of the insulators contained in H, S and V images is computed by the frequency-tuned method. Meanwhile, the primary insulator image is obtained by fusing the saliency information of insulators. Finally, the segmented insulators are obtained by applying Otsu algorithm and opening operation to the significant images, and we locate the insulators by using contour recognition. The experimental results show that the method can accurately identify the insulator string from aerial image with complicated background, which has a high value for engineering application.
Zhu Shaocheng,Gao Qingwei,Lu Yixiang等. Identification and Location of Insulator String Based on Frequency-Tuned[J]. Transactions of China Electrotechnical Society, 2018, 33(23): 5573-5580.
[1] Yan Guangjian, Li Chaoyang, Zhou Guoqing, et al.Automatic extraction of power lines from aerial images[J]. IEEE Geoscience and Remote Sensing Letters, 2007, 4(3): 387-391. [2] 刘文, 杨慧霞, 祝斌. 智能电网技术标准体系研究综述[J]. 电力系统保护与控制, 2012, 40(10): 120-126. Liu Wen, Yang Huixia, Zhu Bin.Review of research on smart grid technical standard system[J]. Power System Protection and Control, 2012, 40(10): 120-126. [3] 高志远, 姚建国, 曹阳, 等. 智能电网发展机理研究初探[J]. 电力系统保护与控制, 2014, 42(5): 116-121. Gao Zhiyuan, Yao Jianguo, Cao Yang, et al.Primary study on the development mechanism of smart grid[J]. Power System Protection and Control, 2014, 42(5): 116-121. [4] 何永秀, 朱茳, 罗涛, 等. 城市电网规划自然灾害风险评价研究[J]. 电工技术学报, 2011, 26(12): 205-210. He Yongxiu, Zhu Jiang, Luo Tao, et al.Risk assessment of natural disaster in urban electric power network planning[J]. Transactions of China Electrotechnical Society, 2011, 26(12): 205-210. [5] 束洪春, 司大军, 葛耀中, 等. 人工神经网络应用于输电线路故障测距研究[J]. 电工技术学报, 2000, 15(6): 61-64. Shu Hongchun, Si Dajun, Ge Yaozhong, et al.Study of applying ANN to locating fault on HV transmission lines[J]. Transactions of China Electrotechnical Society, 2000, 15(6): 61-64. [6] 马帅营, 安居白, 陈舫明. 基于HSI颜色空间的绝缘子图像的分割[J]. 大连民族学院学报, 2010, 12(5): 481-484. Ma Shuaiying, An Jubai, Chen Fangming.Segmentation of insulator images based on HIS color space[J]. Journal of Dalian Nationalities University, 2010, 12(5): 481-484. [7] 黄宵宁, 张真良. 直升机巡检航拍图像中绝缘子图像的提取算法[J]. 电网技术, 2010, 34(1): 194-197. Huang Xiaoning, Zhang Zhenliang.A method to extract insulator image from aerial image of helicopter patrol[J]. Power System Technology, 2010, 34(1): 194-197. [8] 姚春羽, 金立军, 闫书佳. 电网巡检图像中绝缘子的识别[J]. 系统仿真学报, 2012, 24(9): 1818-1822. Yao Chunyu, Jin Lijun, Yan Shujia.Recognition of insulator string in power grid patrol images[J]. Journal of System Simulation, 2012, 24(9): 1818-1822. [9] Li Bingfeng, Wu Denglu, Cong Yang, et al.A method of insulator detection from video sequence[C]//2012 Fourth International Symposium on Information Science and Engineering, Shanghai, 2012: 386-389. [10] 仝卫国. 基于航拍图像的输电线路识别与状态检测方法研究[D]. 保定: 华北电力大学, 2011. [11] 苑津莎, 崔克彬, 李宝树. 基于ASIFT算法的绝缘子视频图像的识别与定位[J]. 电测与仪表, 2015, 52(7): 106-112. Yuan Jinsha, Cui Kebin, Li Baoshu.Identification and location of insulator video images based on ASIFT algorithm[J]. Electrical Measurement & Instrumentation, 2015, 52(7): 106-112. [12] Rafael C G, Richard E W.Digital image processing[M]. 2nd ed. Englewood: Prentice Hall, 2002. [13] Robert L.OpenCV计算机视觉编程攻略[M]. 相银初, 译. 北京: 人民邮电出版社, 2015. [14] 陈帅, 赵海龙, 衣俊艳. 基于HSV空间的创新型车牌定位方法[J]. 电工技术学报, 2015, 30(增刊1): 527-530. Chen Shuai, Zhao Hailong, Yi Junyan.Creative license plate locating method based on HSV space[J]. Transactions of China Electrotechnical Society, 2015, 30(S1): 527-530. [15] 魏昱. 图像显著性区域检测方法及应用研究[D]. 济南: 山东大学, 2012. [16] Achanta R, Hemami S, Estrada F, et al.Frequency-tuned salient region detection[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, 2009: 1597-1604. [17] 周文天, 李军民, 唐慧娟, 等. 基于高斯差分滤波和形态学滤波的Harris角点检测算法[J]. 西华大学学报(自然科学版), 2014, 33(6): 24-27. Zhou Wentian, Li Junmin, Tang Huijuan, et al.Research on Harris corner detection based on Gaussian differential and morphological filter[J]. Journal of Xihua University (Natural Science), 2014, 33(6): 24-27. [18] 殷苏民, 朱锦萍, 王祖声, 等. 基于顶帽变换和最大类间方差法的图像分割方法研究[J]. 科学技术与工程, 2014, 14(7): 60-64. Yin Sumin, Zhu Jinping, Wang Zusheng, et al.Research on image segmentation method based on top-hat transformation and Otsu[J]. Science Technology and Engineering, 2014, 14(7): 60-64. [19] 王璇, 张帆, 程京. 基于改进最大类间方差法的灰度图像分割[J]. 微计算机信息, 2010, 26(35): 406-407. Wang Xuan, Zhang Fan, Cheng Jing.Improved OTSU method on gray level image segmentation[J]. Microcomputer Information, 2010, 26(35): 406-407. [20] Pan Jianjia, Zheng Xianwei, Sun Li, et al.Image segmentation based on 2D OTSU and simplified swarm optimization[C]//2016 International Conference on Machine Learning and Cybernetics (ICMLC), Jeju, 2016: 1026-1030. [21] 王惠华, 游福成, 段怀锋, 等. 基于二值图像连通域提取的图像滤波方法[J]. 北京印刷学院学报, 2015, 23(6): 39-41. Wang Huihua, You Fucheng, Duan Huaifeng, et al.An image filtering method to extract connected domain in binary image[J]. Journal of Beijing Institute of Graphic Communication, 2015, 23(6): 39-41. [22] 张恒, 倪永婧. 面向目标特征提取的连通域标记算法[J]. 计算机与网络, 2015, 41(7): 58-61. Zhang Heng, Ni Yongjing.Connected component labeling algorithm oriented to target feature extraction[J]. Computer & Network, 2015, 41(7): 58-61.
2018, Vol. 33 
