测绘通报 ›› 2020, Vol. 0 ›› Issue (5): 95-100.doi: 10.13474/j.cnki.11-2246.2020.0153

• 学术研究 • 上一篇    下一篇

利用车载点云数据构建建筑物立面窗户模型

范辉龙1, 李永强1, 杨清科2, 李鹏鹏1, 刘亚坤1, 赵上斌1   

  1. 1. 河南理工大学测绘与国土信息工程学院, 河南 焦作 454000;
    2. 河南省水利勘测设计研究有限公司, 河南 郑州 450000
  • 收稿日期:2019-08-12 修回日期:2020-03-22 出版日期:2020-05-25 发布日期:2020-06-02
  • 作者简介:范辉龙(1993-),男,硕士,主要研究方向为3S集成与应用。E-mail:1657354895@qq.com
  • 基金资助:
    测绘地理信息公益性行业科研专项(201412020);国家自然科学基金(41771491)

Building facade window model construction of vehicle point cloud data

FAN Huilong1, LI Yongqiang1, YANG Qingke2, LI Pengpeng1, LIU Yakun1, ZHAO Shangbin1   

  1. 1. School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, China;
    2. Henan Water Conservancy Survey Design Research Co., Ltd., Zhengzhou 450000, China
  • Received:2019-08-12 Revised:2020-03-22 Online:2020-05-25 Published:2020-06-02

摘要: 采用车载LiDAR数据进行窗户模型构建是一项艰巨的工作,本文提出了一整套窗户模型构建方法。首先利用RANSAC算法对建筑物立面进行探测分离主墙面,基于空洞思想对主墙面窗户进行聚类,然后采用动态椭圆凸壳算法探测窗户边界轮廓点。对获取窗户边界点采用RANSAC算法进行分割,采用基于稳健整体最小二乘算法进行直线拟合和角点恢复,最终结合窗户的几何特征完成窗户模型构建。试验结果证明了该方法能够准确有效地构建建筑物立面中的窗户模型。

关键词: 车载LiDAR, 建筑物立面, RANSAC, 聚类分割, 模型构建

Abstract: Using vehicle LiDAR data to build window model is a hard work. First, the RANSAC algorithm is used to detect and separate the main wall of the building facade, and the Windows on the main wall are clustered based on empty ideas. Then, the dynamic elliptic convex hull algorithm is used to detect the boundary contour points of windows. The obtained window boundary points are segmented by RANSAC algorithm, and the linear fitting and corner point restoration are carried out by using the robust global least squares algorithm. Finally, the window model construction is completed by combining the geometric features of the Windows. The experimental results show that this method can accurately and effectively construct window models in building facades.

Key words: vehicle LiDAR, building façade, RANSAC, clustering segmentation, model building

中图分类号: