摘要
针对输电线路提取方法的现有研究,分析了当前主流的电力线提取方法--LSD (Line Segment Detecto)算法,根据算法的基本原理及电力线的布设特征,设计了一种结合图像增强和LSD算法的无人机影像电力线提取方法,首先对图像进行预处理和图像增强,结合Canny算子对图像进行LSD算法提取,将结果中的小线段进一步提取出像素点的坐标,之后根据筛选后的像素点坐标进行线段拟合,得到最终电力线结果。采用无人机航拍的影像进行实验。结果表明,本方法在复杂地物背景下对电力线提取的检测速度较快,稳健性强。对电力巡线具有较大的实际意义。
Based on the existing research on transmission line extraction method, the current mainstream power line extraction method, LSD(Line Segment Detecto) algorithm, is designed. Based on the basic principle of the algorithm and the layout characteristics of power lines, a combination of image enhancement and LSD is designed. The algorithm of UAV image power line extraction method firstly preprocesses and enhances the image, combines the Canny operator to extract the image by LSD algorithm, and further extracts the co l ordinates of the pixel from the small line segment in the result, and then according to the selected Line segment fitting is performed on the pixel coordinates to obtain the final power line result. The experiment is carried out with the aerial image of the drone. The results show that the method is faster and more robust when the power line is extracted under the complex ground object background. It has great practical significance for the power line.
作者
刘思雨
吕开云
刘盈
LIU Siyu;LYU Kaiyun;LIU Ying(School of Mapping Engineering,East China University of Technology,330013,Nanchang,PRC;School of Electronical and Information Engineering,Jinggangshan University,343009,Ji′an,Jiangxi,PRC)
出处
《江西科学》
2019年第6期825-831,共7页
Jiangxi Science
基金
江西省自然科学基金(20151BAB203042)
江西省教育厅科技项目(GJJ150591)
放射性地质与勘探技术国防重点学科实验室基金(REGT1219)
