基于点云数据的建筑物屋顶面点集轮廓线提取  

Outline extraction of the building roof point set based on point cloud data

作　　者：王道芸 袁晨鑫 WANG Daoyun;YUAN Chenxin(Guangzhou Urban Renewal Planning&Design Institute Company Limited,Guangzhou Guangdong 510000,China;China Nuclear Industry Group Company Limited,Xi’an Shaanxi 710000,China)

机构地区：[1]广州市城市更新规划设计研究院有限公司,广东广州510000 [2]中陕核工业集团测绘院有限公司,陕西西安710000

出　　处：《北京测绘》2023年第6期861-866,共6页Beijing Surveying and Mapping

摘　　要：针对利用点云数据提取建筑物轮廓线不完整、缺失的问题,提出一种基于点云数据提取建筑物轮廓线方法。该方法首先对原始点云数据进行预处理,获取建筑物点云数据集;其次,采用具有噪声的基于密度的聚类方法(DBSCAN)进行点集聚类,得到单个建筑物点云数据集;再次,采用Alpha Shapes算法进行建筑物轮廓线粗提取,然后采用管子算法进行建筑物特征关键点提取;最后采用强制正交的方法进行轮廓线规则化,获取最终的建筑物轮廓线。实验证明,本文方法可以很好地提取建筑物轮廓线,适用性和时效性比较好。Aiming at the problem that the extract buildings with point cloud is incomplete and missing,a kind of outline extraction method based on point cloud data was put forward for buildings.Firstly,the original point cloud data was processed to obtain the building point cloud data set.Then,point clustering based on density-based spatial clustering of applications with noise(DBSCAN)method was applied to obtain a single building point cloud data set.Secondly,Alpha Shapes algorithm was explored to extract the building contour,and then the pipe algorithm was used for extraction of the building key points.Finally,the forced orthogonal method was applied to regularize the contour and obtain the final building outlines.Experiments showed that the proposed method could extract building contour lines well,with good applicability and timeliness.

关 键 词：点云数据 具有噪声的基于密度的聚类方法 Alpha Shapes算法 管子算法 强制正交规则化 

分 类 号：P258[天文地球—测绘科学与技术]