基于机载LiDAR点云数据的建筑物三维模型重建方法

3D Building Model Reconstruction Method Based on Airborne LiDAR Point Cloud Data

摘要: 本文以机载LiDAR点云数据为研究对象，提出一套建筑物三维模型重建方法。首先使用渐进三角网滤波算法分类地面点与非地面点，通过训练完成的随机森林模型完成建筑物点云提取；其次将方向作为约束条件，使用随机抽样一致(Random Sample Consensus, RANSAC)算法完成建筑物轮廓线提取并获取屋顶关键点信息；最后使用SharpGL工具包，以建筑物轮廓线与屋顶关键点信息为框架重建建筑物三维模型。以实测机载LiDAR点云数据为例进行实验，结果表明本文方法能够提取得到完整的建筑物轮廓信息，并具有较高的建筑物模型重建精度。

Abstract: Based on the airborne LiDAR point cloud data, this paper proposes a set of building 3D model re-construction methods. Firstly, the gradual triangulation filtering algorithm is used to classify ground points and non-ground points, and the building point cloud is extracted through the trained random forest model; secondly, the direction is taken as the constraint condition, and the random sample consistent (RANSAC) algorithm is used to extract the building contour line and obtain the roof key point information; finally, the SharpGL toolkit is used to reconstruct the 3D model of the building based on the building outline and roof key point information. Taking the measured air-borne LiDAR point cloud data as an example, the experimental results show that the proposed method can extract complete building contour information, and has high building model recon-struction accuracy.