基于输电线树障定位的改进欧氏聚类分割算法研究  被引量:1

Research on improved Euclidean clustering and segmentation algorithm based on transmission line tree barrier positioning

在线阅读下载全文

作  者:施保华[1,2] 朱正基 刘伟 SHI Baohua;ZHU Zhengji;LIU Wei(College of Electrical Engineering and New Energy,Three Gorges University,Yichang 443002,China;Hubei Microgrid Engineering Technology Research Center,Yichang 443002,China)

机构地区:[1]三峡大学电气与新能源学院,湖北宜昌443002 [2]湖北省微电网工程技术研究中心,湖北宜昌443002

出  处:《广西大学学报(自然科学版)》2023年第5期1124-1133,共10页Journal of Guangxi University(Natural Science Edition)

基  金:国家自然科学基金项目(61876097)。

摘  要:为了提高输电线路巡检的树障定位精确度,提出了一种基于改进欧氏聚类分割的三维点云树障定位方法。该方法利用无人机采集图片进行三维模型重建,通过降采样、位姿调整及滤波对三维点云进行预处理;对于不同类型的树障环境,提出一种前K点柱状约束的欧氏聚类分割算法,提取巡检区域的单簇输电线点云;利用随机采样一致及最小二乘法拟合输电线电云的空间方程,计算非输电线点云与输电线点云的距离,并依据电网安全树线距离定位树障的位置。经过2种不同树障情况的实验,证明此方法可以有效地解决输电线路树障的定位问题。In order to enhance the accuracy of tree obstacle localization in transmission line inspections,a three-dimensional point cloud tree obstacle localization method based on improved Euclidean clustering segmentation is proposed.This method utilizes unmanned aerial vehicles(UAVs)to capture images for three-dimensional model reconstruction.The three-dimensional point cloud is preprocessed through downsampling,pose adjustment,and filtering.Moreover,for different types of tree obstacle environments,an Euclidean clustering segmentation algorithm with a front K-point cylindrical constraint is proposed to extract the point cloud of single clusters in the inspection area.The spatial equation of the transmission line is fitted using the random sample consensus(RANSAC)and the least squares method to calculate the distance between non-transmission line points and transmission line points.The position of the tree obstacle is determined based on the distance from the power grid s safe tree line distance.Through experiments conducted with two different tree obstacle scenarios,it is demonstrated that this method effectively resolves the localization problem of tree obstacles in transmission lines.

关 键 词:三维重建 位姿调整 欧氏聚类分割 树障定位 

分 类 号:TM755[电气工程—电力系统及自动化]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象