计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (10): 5-7.

• 博士论坛 • 上一篇    下一篇

从LiDAR数据中提取建筑物平面目标的新方法

李云帆,马洪超   

  1. 武汉大学 遥感信息工程学院,武汉 430079
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-04-01 发布日期:2011-04-01

New method for building planar objects extraction from LiDAR data

LI Yunfan,MA Hongchao   

  1. School of Remote Sensing Information Engineering,Wuhan University,Wuhan 430079,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-04-01 Published:2011-04-01

摘要: 提出一种从机载LiDAR点云数据中自动提取建筑物平面的方法。给出了基于边长约束的三角形生长算法对建筑物初始区域进行提取,针对提取出的建筑物脚点,利用自适应Mean Shift方法在特征空间中对其进行聚类分析,并提取出平面目标,最后利用Alpha-Shape算法生成建筑物平面的轮廓线。通过实验证实了方法的有效性。

关键词: LiDAR数据, 自适应Mean Shift, 聚类分析, 建筑物, 平面提取

Abstract: A new method for extracting building planar objects from LiDAR data base on adaptive Mean Shift algorithm is proposed,which consists of three parts:building region detection from filtered LiDAR data using a triangle group algorithm constrained by triangle side length;planar object extraction from building foot prints based on cluster analysis in feature space by adaptive Mean Shift;planar object contour generation using Alpha-Shape algorithm.Experiment is conducted to demonstrate the efficiency of the proposed method.

Key words: LiDAR data, adaptive Mean Shift, cluster analysis, building, planar extraction