激光雷达点云电力线自动提取算法

针对当前电力线提取方法自动化程度和精度不高的问题，本文从点云数据的空间分布特征出发，提出了一种高效的电力线自动提取方法。首先基于自然裂点法，将点云数据按高程分类后去除地面点；然后对数据进行空间划分，基于子空间的点密度及空间结构特征的差异化，利用地物分割算法去除电塔点和残留的植被点；最后利用基于欧氏距离分割的电力线自动检测算法，实现单根电力线的快速、高精度提取。提取结果和拟合试验表明，该方法能在复杂地形下实现电力线的自动提取，极大提高了电力线的提取效率和精度。

An automatic algorithm of power line extraction from LiDAR point cloud

Aiming at the problem of low automation and accuracy of current power line extraction methods, this paper proposes an automatic power line extraction method based on the spatial distribution characteristics of point cloud data. Firstly, based on the nature breaks, the point cloud data is classified according to the elevation, and the ground points are removed. Then, the data is partitioned spatially. Based on the point density of subspace and the difference of spatial structure features, the pylon points and residual vegetation points are removed by ground object segmentation algorithm. Finally, the power line automatic detection algorithm based on Euclidean distance is used to realize the fast and high-precision extraction of a single power line.The results of extraction and fitting experiments show that this method can automatically extract power lines in complex terrain, and greatly improve the efficiency and accuracy of power line extraction.