基于激光点云的室内结构二、三维一体化建模方法  

The integrated 2D and 3D indoor structure modeling based on lazer point cloud

在线阅读下载全文

作  者:魏域君 李丹[2] 刘亚林[2] 刘雨鑫 陈富强 WEI Yujun;LI Dan;LIU Yalin;LIU Yuxin;CHEN Fuqiang(State Key Laboratory of Intelligent Construction and Maintenance for Geotechnical and Tunnel Engineering under Extreme Environments,Xi’an,Shaanxi 710043,China;China Railway First Survey and Design Institute Group Co.,Ltd.,Xi’an,Shaanxi 710043,China)

机构地区:[1]极端环境岩土和隧道工程智能建养全国重点实验室,陕西西安710043 [2]中铁第一勘察设计院集团有限公司,陕西西安710043

出  处:《测绘技术装备》2025年第1期126-132,共7页Geomatics Technology and Equipment

摘  要:目前,基于激光点云数据进行室内建模的常用方法是利用建模软件纯手工建模。针对该类方法带来的效率低下和劳动强度大等问题,本文提出了一种基于激光点云数据的室内结构二、三维一体化建模方法。首先,通过点云切片与二维投影过滤了大量冗余信息;其次,基于点云平面投影结果,利用自动化识别算法进行室内结构绘制;最后,基于室内结构平面图和竖直切片点云分析得到的层高进行室内结构三维建模。实验结果表明,本文方法室内建模结果可基本还原实际结构,几何精度优于5 cm,能够明显提升室内建模的简易性和效率。The indoor 3D modeling method based on laser point cloud data used at present is mainly manual modeling by using modeling software.In order to solve such problems as the poor efficiency and large labor intensity caused by the above method,this paper proposes an integrated 2D and 3D in‐door structure modeling method based on laser point cloud data.This method filters a large amount of redundant information through point cloud slicing and 2D projection,then it uses an automatic recogni‐tion algorithm to draw the indoor structure based on the horizontal point cloud projection,and finally,it carries out the indoor structure 3D modeling based on the floor height obtained by analyzing the hori‐zongtal indoor structure and the vertically sliced point cloud.The experimental results show that the modeling results from the proposed method can basically restore the real indoor structure with a geo‐metric accuracy better than 5 cm,it can significantly improve the simplicity and efficiency of 3D indoor modeling.

关 键 词:激光点云 室内建模 点云切片 点云投影 结构分析 

分 类 号:P232[天文地球—摄影测量与遥感]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象