地理空间信息2025，Vol.23Issue(3)：58-60,65,4.DOI:10.3969/j.issn.1672-4623.2025.03.014
利用自适应邻域特征估算与优选提取电力线
Power Line Extraction Based on Self-adaptive Neighborhood Feature Estimation and Optimization
摘要
Abstract
In response to the demand of power line information extraction in rapid power inspection under complex terrain,based on airborne LiDAR data,we proposed a power line extraction algorithm based on self-adaptive neighborhood feature estimation and optimization.Firstly,based on the elevation characteristics of power lines,we separated non power line points.Then,we constructed multi-dimensional point cloud features based on self-adaptive neighborhood,and used the support vector machine-recursive feature elimination(SVM-RFE)algorithm to achieve optimal feature selection.Finally,we combined the optimal features,and used SVM and random forest method to classify point cloud,achieving the extraction of power lines.The result indicates that this method has high accuracy in power line information extraction and high applicability.关键词
机载LiDAR/电力线/自适应邻域/特征优选Key words
airborne LiDAR/power line/self-adaptive neighborhood/optimal feature selection分类
天文与地球科学引用本文复制引用
袁超,李元达,陈昌耀,刘建明..利用自适应邻域特征估算与优选提取电力线[J].地理空间信息,2025,23(3):58-60,65,4.基金项目
基于新一代星载LiDAR数据的中国30m分辨率森林高度反演研究(42071405). （42071405）
