摘要
电力设备故障会导致停电事故,影响电网的安全稳定运行。根据电力设备运行时会产生热量的特点,提出一种电力设备的红外与可见光图像配准方法,便于进行异常发热故障检测。首先通过Sobel边缘检测算子提取电力设备的红外与可见光图像的边缘信息,得到边缘图像;然后通过SuperPoint算法检测2幅边缘图像的特征点并计算描述子,利用SuperGlue算法对特征点进行匹配;最后通过最小二乘法计算仿射变换模型参数,实现电力设备的红外与可见光图像配准。实验结果表明本文方法能够对电力设备的红外与可见光图像进行高精度的配准。
The failure of power equipment may cause power outages and affect the safe and stable operation of power grid.According to the characteristics of heat generated by power equipment during operation,an infrared and visible images registration method for power equipment is proposed to facilitate detection of abnormal heating faults.Firstly,the Sobel edge detection operator extracts edge information from infrared and visible images of power equipment to obtain edge images.Then the feature points of two edge images are detected by the SuperPoint algorithm and the descriptors are calculated,and the feature points are matched by the SuperGlue algorithm.Finally,the affine transformation model parameters are calculated by the least square method to realize the infrared and visible image registration of power equipment.The experimental results show that the method in this paper can achieve high-precision registration of infrared and visible images of power equipment.
作者
刘晓康
夏天雷
吴晨媛
姜雄彪
周明玉
王庆华
LIU Xiao-kang;XIA Tian-lei;WU Chen-yuan;JIANG Xiong-biao;ZHOU Ming-yu;WANG Qing-hua(State Grid Changzhou Power Supply Company, Changzhou 213000, China;College of Internet of Things Engineering, HoHai University, Changzhou 213022, China;Changzhou Zhongneng Power Technology Co. Ltd., Changzhou 213000, China)
出处
《计算机与现代化》
2021年第9期31-36,42,共7页
Computer and Modernization
基金
江苏省重点研发项目(BE2020092)
国网常州供电公司项目(SGTYHT/19-JS-218)。
关键词
图像配准
电力设备
边缘图像
深度学习
神经网络
image registration
power equipment
edge image
deep learning
neural network
作者简介
刘晓康(1986—),男,江苏常州人,高级工程师,硕士,研究方向:电气工程,E-mail:70551313@qq.com;夏天雷(1990—),男,工程师,硕士,研究方向:电气工程,E-mail:xtlchina@sina.com;吴晨媛(1991—),女,助理工程师,硕士,研究方向:电气工程,E-mail:704345213@qq.com;通信作者:姜雄彪(1999—),男,河北邯郸人,硕士研究生,研究方向:信息获取与处理,E-mail:694929605@qq.com。
