基于车载激光扫描技术的行道树提取方法研究

Street tree extraction method based on vehicle laser scanning technology

为了提高基于车载激光点云数据的行道树提取效率与准确率,本文提出了一种改进区域增长方法,并将其应用到车载激光点云数据的行道树点云数据提取中。首先分层格网化点云数据,接着对行道树在格网中的分布形态进行分析,同时结合点云的高程分布特征、点云密度特征及其他特征,使用区域增长方法提取得到点云场景中的行道树点云数据。实验结果表明,本文使用的方法能够将干扰行道树提取的地面低矮植点等地物点云数据消除,实现行道树的准确提取,结果误差较小,精度较高。

In order to improve the efficiency and accuracy of street tree extraction based on vehicle laser point cloud data,an improved region growth method is proposed and applied to the roadside tree point cloud data extraction of vehicle laser point cloud data in this paper.The point cloud data is firstly layered,and the distribution pattern of street tree in the grid is then analyzed.At the same time,combined with the elevation distribution characteristics,density characteristics and other characteristics of point cloud,the point cloud data of street tree in point cloud scene is extracted by using the method of regional growth.The experimental results show that the method used in this paper can eliminate such ground point cloud data that are low vegetation points who interfere with the extraction of street trees,and achieve accurate street tree extraction with small error and high precision.