北京测绘2026，Vol.40Issue(2)：184-189,6.DOI:10.19580/j.cnki.1007-3000.2026.02.008
基于分水岭算法与同质区合并的机载LiDAR点云数据分割方法
Airborne LiDAR point cloud data segmentation method based on watershed algorithm and homogeneous region merging
冯待飞 1周东茂1
作者信息
- 1. 中国冶金地质总局第三地质勘查院,山西 太原 030031
- 折叠
摘要
Abstract
In response to the problems of excessive image overlap and low segmentation accuracy in the point cloud data seg-mentation process of airborne light detection and ranging(LiDAR)in real estate measurement,this paper adopted a method based on the watershed algorithm and homogeneous region merging to carry out the design and research of an airborne LiDAR point cloud data segmentation method.It improved the quality of point cloud data through preprocessing steps such as denoising,filtering,and normalization.Subsequently,the watershed algorithm was used to partition the image feature regions,and a homogeneous region merging algorithm was designed based on the merging criterion to optimize the segmenta-tion effect of point cloud data.The experimental results show that this method can not only effectively optimize the vertical segmentation of LiDAR point cloud data density and the horizontal segmentation of surface feature images but also signifi-cantly control the overlap of segmented images,improving segmentation accuracy and efficiency.The point cloud data seg-mentation method based on the watershed algorithm and homogeneous region merging proposed in this paper provides an effi-cient and accurate solution for real estate measurement.关键词
分水岭算法/区域合并/分割方法/点云数据/不动产测量Key words
watershed algorithm/region merging/segmentation method/point cloud data/real estate measurement分类
农业科技引用本文复制引用
冯待飞,周东茂..基于分水岭算法与同质区合并的机载LiDAR点云数据分割方法[J].北京测绘,2026,40(2):184-189,6.
