一种古建筑点云数据的语义分割算法

张瑞菊; 周欣; 赵江洪; 曹闵

doi:10.13203/j.whugis20180428

一种古建筑点云数据的语义分割算法

张瑞菊^{1, 2, 3,},
周欣^{1, 4, ,},
赵江洪^{1, 2, 3},
曹闵⁵

1.
北京建筑大学测绘与城市空间信息学院, 北京, 102616
2.
代表性建筑与古建筑数据库教育部工程中心, 北京, 102616
3.
建筑遗产精细重构与健康监测重点实验室, 北京, 102616
4.
武汉珞珈新空科技有限公司, 湖北武汉, 430223
5.
北京建工建筑设计研究院, 北京, 102616

基金项目:

国家自然科学基金 41501495

国家自然科学基金 41601409

北京建筑大学市属高校基本科研业务费专项资金 X18228

北京建筑大学市属高校基本科研业务费专项资金 X18290

精密工程与工业测量国家测绘地理信息局重点实验室开放研究基金 PF2013‐1

北京市自然科学基金 8172016

城市空间信息工程北京市重点实验室开发研究基金 2018210

详细信息

作者简介:
张瑞菊, 博士, 讲师, 主要从事三维激光点云数据处理研究。zhangruiju@bucea.edu.cn

通讯作者:
周欣: ZHOU Xin, master. E‐mail: bingchengguyan@foxmail.com

中图分类号: P237
计量
- 文章访问数: 1773
- HTML全文浏览量: 335
- PDF下载量: 142
出版历程
- 收稿日期: 2019-09-27
- 发布日期: 2020-05-04

A Semantic Segmentation Algorithm of Ancient Building's Point Cloud Data

ZHANG Ruiju^{1, 2, 3,},
ZHOU Xin^{1, 4, ,},
ZHAO Jianghong^{1, 2, 3},
CAO Min⁵

1.
School of Geomantic and Urban Information, Beijing University of Civil Engineering and Architecture, Beijing 102616, China
2.
Engineering Research Center of Representative Building and Architectural Heritage Database, Ministry of Education, Beijing 102616, China
3.
Beijing Key Laboratory for Architectural Heritage Fine Reconstruction & Health Monitoring, Beijing 102616, China
4.
Wuhan RGSpace Technology Co. Ltd, Wuhan 430223, China
5.
Beijing Jiangong Architecture Design and Research Institute, Beijing 102616, China

Funds:

The National Natural Science Foundation of China 41501495

The National Natural Science Foundation of China 41601409

the Fundamental Research Funds for the Municipal Universities of Beijing University of Civil Engineering and Architecture X18228

the Fundamental Research Funds for the Municipal Universities of Beijing University of Civil Engineering and Architecture X18290

the Open Foundation of Key Labora‐ tory of Precise Engineering and Industry Surveying of National Administration of Surveying, Mapping and Geoinformation PF2013‐1

Bei‐ jing Municipal Natural Science Foundation 8172016

the Open Foundation of Beijing Key Laboratory of Urban Spatial Information Engi‐ neering 2018210

More Information

Author Bio:
ZHANG Ruiju, PhD, lecturer, specializes in 3D laser scanning point cloud data processing. E‐mail: zhangruiju@bucea.edu.cn

摘要

摘要: 针对目前从三维激光扫描点云中进行古建筑木构件分割较难的现状，提出一种对古建筑点云数据进行精确、快速语义分割的新算法。该算法首先对点云进行去噪处理；然后利用古建筑结构特性定义与柱构件相交且垂直于坐标系竖轴的一个截面并提取截面点云；接着利用点云欧氏聚类的方法从截面点云数据中提取对应于柱构件的点云并估计柱构件参数，进而基于罗德里格旋转矩阵将古建筑点云数据自动转正，使点云三维坐标系的竖轴严格垂直于地面；最后基于模型拟合的方法分割出柱构件点云，并利用古建筑几何结构、尺寸等信息采用基于包围盒的方法对其他木构件（如梁、枋等）进行分割。为了验证算法的稳健性与可行性，选取亭子类古建筑点云数据进行实验与分析。结果表明，该算法具有一定的可行性与稳健性，为古建筑点云的自动语义分割提供了思路与方法。
- 三维激光扫描 /
- 古建筑 /
- 木构件 /
- 点云 /
- 语义分割
Abstract: In view of the difficulty of wooden elements segmentation of three-dimensional laser scanning point cloud data of ancient building, a new algorithm for effective and accurate segmentation of ancient building's point clouds is presented. Firstly, point cloud denoising is implemented. Then a section intersecting with wooden columns and being perpendicular to the vertical axis of the three-dimensional coordinate system is created based on structural characteristics of ancient buildings. At the same time, point clouds on the section are extracted and divided into several parts which are corresponding to different wooden columns based on point cloud Euclidean clustering. Parameters of wooden columns are estimated and used to compute the Rodrigo rotation matrix in order to implement automatic spatial transformation of ancient building's point clouds. By this processing, vertical axis of the three-dimensional coordinate system will be strictly perpendicular to the ground. And then point clouds of wooden columns are extracted by model fitting method. Other wooden elements (such as beams, tiebeams etc.) are segmented out by bounding box created by the information of structure and size of ancient building. In order to prove the robustness and feasibility of the algorithm, the point clouds of pavilions are selected for the experiment in this study. The result shows that the algorithm is feasible and robust. This research can provide supports of theory and methods for deeply research of automatic segmentation of ancient building's point cloud data.
- 3D laser scanning /
- ancient building /
- wooden elements /
- point cloud /
- semantic segmentation

HTML全文

图 1 木构件分割流程图

Figure 1. Flowchart of Wooden Elements Segmentation

下载: 全尺寸图片幻灯片

图 2 噪点去除示意图

Figure 2. Diagram of Noise Removal

下载: 全尺寸图片幻灯片

图 3 基于柱轴线构建构件包围盒

Figure 3. Creating Wooden Element Boundary Box Based on Wooden Column Axis

下载: 全尺寸图片幻灯片

图 4 实验数据

Figure 4. Experimental Data

下载: 全尺寸图片幻灯片

图 5 点云转正示意图

Figure 5. Diagram of Point Cloud's Space Transformation

下载: 全尺寸图片幻灯片

图 6 柱构件分割结果

Figure 6. Segmentation Result of Wooden Columns

下载: 全尺寸图片幻灯片

图 7 梁、枋的尺寸和位置参数

Figure 7. Size and Position Parameters of Beams and Tiebeams

下载: 全尺寸图片幻灯片

图 8 分层次分割木构件

Figure 8. Hierarchical Segmentations of Wooden Elements

下载: 全尺寸图片幻灯片

图 9 实验数据最终分割结果

Figure 9. Final Segmentation Result of the Experimental Data

下载: 全尺寸图片幻灯片

参考文献(21)

[1]	张瑞菊.基于三维激光扫描数据的古建筑构件三维重建技术研究[D].武汉: 武汉大学, 2006 http://cpfd.cnki.com.cn/Article/CPFDTOTAL-CMJH200912001029.htm Zhang Ruiju. 3D Reconstruction of Ancient Building Components Based on 3D Laser Range Data[D]. Wuhan: Wuhan University, 2006 http://cpfd.cnki.com.cn/Article/CPFDTOTAL-CMJH200912001029.htm
[2]	杨必胜, 梁福逊, 黄荣刚.三维激光扫描点云数据处理研究进展、挑战与趋势[J].测绘学报, 2017, 46(10):1509-1516 doi: 10.11947/j.AGCS.2017.20170351 Yang Bisheng, Liang Fuxun, Huang Ronggang. Progress, Challenges and Perspectives of 3D LiDAR Point Cloud Processing[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10):1509-1516 doi: 10.11947/j.AGCS.2017.20170351
[3]	索俊锋, 刘勇, 蒋志勇, 等.基于三维激光扫描点云数据的古建筑建模[J].测绘科学, 2017, 42(3):179-185 http://d.old.wanfangdata.com.cn/Periodical/chkx201703033 Suo Junfeng, Liu Yong, Jiang Zhiyong, et al. Modeling of Ancient Building Based on 3D Laser Scanning Point Cloud Data[J]. Science of Surverying and Mapping, 2017, 42(3):179-185 http://d.old.wanfangdata.com.cn/Periodical/chkx201703033
[4]	陆建华, 吕志才.基于多时相点云数据的大型古建筑形变监测研究——以苏州虎丘塔为例[J].工程勘察, 2016, 44(7):53-58 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gckc201607012 Lu Jianhua, Lü Zhicai. Deformation Monitoring of Large Ancient Architectural Buildings Based on Multi-temporal Point Cloud:A Case Study of Suzhou Tiger Hill Pagoda[J]. Geotechnical Investigation & Surveying, 2016, 44(7):53-58 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gckc201607012
[5]	盛德新, 杨振球.基于激光点云数据的古建筑BIM几何模型构建[J].测绘工程, 2015, 24(7):76-80 doi: 10.3969/j.issn.1006-7949.2015.07.018 Sheng Dexin, Yang Zhenqiu. Construction of Geometric Models of Ancient Buildings Based on Laser Point Cloud Data[J]. Engineering of Surveying and Mapping, 2015, 24(7):76-80 doi: 10.3969/j.issn.1006-7949.2015.07.018
[6]	Grilli E, Menna F, Remondino F. A Review of Point Clouds Segmentation and Classification Algorithms[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017, XLII-2/W3:339-344 doi: 10.5194/isprs-archives-XLII-2-W3-339-2017
[7]	Nguyen A, Le B. 3D Point Cloud Segmentation: A Survey[C]. The 6th IEEE International Conference on Robotics, Automation and Mechatronics, Manila, Philippines, 2013
[8]	Bhanu B, Lee S, Ho C C, et al. Range Data Processing: Representation of Surfaces by Edges[C]. The 8th International Conference on Pattern Recognition, Paris, France, 1986 https://www.researchgate.net/publication/282828645_RANGE_DATA_PROCESSING_REPRESENTATION_OF_SURFACES_BY_EDGES
[9]	Besl P J, Jain R C. Segmentation Through Variable-Order Surface Fitting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1988, 10(2):167-192 doi: 10.1109/34.3881
[10]	Dong Z, Yang B, Hu P, et al. An Efficient Global Energy Optimization Approach for Robust 3D Plane Segmentation of Point Clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 137:112-133 doi: 10.1016/j.isprsjprs.2018.01.013
[11]	Zhang Ruiju, Wang Yanmin, Li Deren, et al. Segmentation of Wooden Members of Ancient Architecture from Range Image[J]. Proceedings of SPIE-The International Society for Optical Engineering, 2006, doi: 10.1117/12.713254
[12]	Schnabel R, Wahl R, Klein R. Efficient RANSAC for Point-Cloud Shape Detection[J]. Computer Graphics Forum, 2007, 26(2):214-226 doi: 10.1111/j.1467-8659.2007.01016.x
[13]	张良培, 张云, 陈震中, 等.基于分裂合并的多模型拟合方法在点云分割中的应用[J].测绘学报, 2018, 47(6):833-843 http://d.old.wanfangdata.com.cn/Periodical/chxb201806017 Zhang Liangpei, Zhang Yun, Chen Zhenzhong, et al. Splitting and Merging Based Multi-model Fitting for Point Cloud Segmentation[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(6):833-843 http://d.old.wanfangdata.com.cn/Periodical/chxb201806017
[14]	Filin S. Surface Clustering from Airborne Laser Scanning Data[J]. International Archives of Photogrammetry, Remote Sensing and Spatial-Information Sciences, 2002, XXXIV(3A/B):119-124 http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ025466494/
[15]	Armeni I, Sener O, Zamir A R, et al. 3D Semantic Parsing of Large-Scale Indoor Spaces[C]. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016 https://www.researchgate.net/publication/311609138_3D_Semantic_Parsing_of_Large-Scale_Indoor_Spaces
[16]	黄荣刚, 杨必胜, 李健平, 等.利用目标区域拓扑关系图提取建筑物点云[J].武汉大学学报·信息科学版, 2017, 42(4):475-481 http://ch.whu.edu.cn/CN/abstract/abstract5705.shtml Huang Ronggang, Yang Bisheng, Li Jianping, et al. Building Points Detection from Airborne LiDAR Point Clouds Using Topological Relationship Graph Within Each Object Region[J]. Geomatics and Information Science of Wuhan University, 2017, 42(4):475-481 http://ch.whu.edu.cn/CN/abstract/abstract5705.shtml
[17]	Qi C R, Su H, Mo K, et al. Pointnet: Deep Learning on Point Sets for 3D Classification and Segmentation[C]. IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, USA, 2017 https://www.researchgate.net/publication/311411614_PointNet_Deep_Learning_on_Point_Sets_for_3D_Classification_and_Segmentation
[18]	Landrieu L, Simonovsky M. Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs[C]. IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, USA, 2018 https://www.researchgate.net/publication/321325284_Large-Scale_Point_Cloud_Semantic_Segmentation_with_Superpoint_Graphs
[19]	熊汉江, 郑先伟, 丁友丽, 等.基于2D-3D语义传递的室内三维点云模型语义分割[J].武汉大学学报·信息科学版, 2018, 43(12):550-556 http://ch.whu.edu.cn/CN/abstract/abstract6320.shtml Xiong Hanjiang, Zheng Xianwei, Ding Youli, et al. Semantic Segmentation of Indoor 3D Point Cloud Model Based on 2D-3D Semantic Transfer[J]. Geomatics and Information Science of Wuhan University, 2018, 43(12):550-556 http://ch.whu.edu.cn/CN/abstract/abstract6320.shtml
[20]	Hackel T, Savinov N, Ladicky L, et al. Semantic3D. net:A New Large-scale Point Cloud Classification Benchmark[J]. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017, doi: 10.5194/isprs-annals-Ⅳ-1-W1-91-2017
[21]	朱德海.点云库PCL学习教程[M].北京:北京理工大学出版社, 2015 Zhu Dehai. Point Cloud Library PCL Learning Tutorial[M]. Beijing:Beijing Institute of Technology Press, 2015

施引文献(24)

期刊类型引用(14)

1.	刘学习，朱守庆，陈国，张克非，郑南山，刘婧璇. 基于全球统一坐标框架的GNSS精密轨道与钟差产品一致性分析. 测绘学报. 2025(03): 432-447 . 百度学术
2.	冯晓亮，陈欢，李厚芝. 不同观测环境中的多模GNSS数据质量自动化检测方法. 测绘工程. 2024(06): 56-61 . 百度学术
3.	刘嘉伟，孙保琪，韩蕊，张喆，王侃，袁海波，杨旭海. GNSS多系统RTK授时性能分析. 导航定位与授时. 2023(03): 49-58 . 百度学术
4.	王浩浩，郝明，庄文泉. GNSS实时卫星钟差估计在地震监测中的应用. 导航定位与授时. 2023(03): 108-116 . 百度学术
5.	周长江，余海锋，王林伟，雷云平，岳彩亚. 无频间钟偏差改正的BDS-2三频非组合PPP随机模型优化. 测绘通报. 2023(12): 164-168 . 百度学术
6.	潘丽静，刘翔，夏川茹，王雷雷. GNSS精密卫星钟差实时估计与分析. 城市勘测. 2021(06): 73-76 . 百度学术
7.	郭磊，王甫红，桑吉章，张万威. 一种新的利用历元间位置变化量约束的GNSS导航算法. 武汉大学学报(信息科学版). 2020(01): 21-27 . 百度学术
8.	陶钧，张柔. GPS/BeiDou/Galileo/GLONASS实时精密卫星钟差估计. 测绘地理信息. 2020(03): 102-106 . 百度学术
9.	黄观文，王浩浩，谢威，曹钰. GNSS实时卫星钟差估计技术进展. 导航定位与授时. 2020(05): 1-9 . 百度学术
10.	张浩，赵兴旺，陈佩文，谢毅. GPS/BDS卫星钟差融合解算模型及精度分析. 合肥工业大学学报(自然科学版). 2020(09): 1192-1196 . 百度学术
11.	叶珍，李浩军. GNSS卫星钟差估计与结果分析. 导航定位与授时. 2019(03): 88-94 . 百度学术
12.	盛剑锋，张彩红，谭凯. 一种全球导航卫星系统钟差估计优化方案的量化研究. 科学技术与工程. 2019(14): 14-21 . 百度学术
13.	王尔申，赵珩，曲萍萍，庞涛，孙军. 基于拉格朗日插值法的卫星导航空间信号精度评估算法. 沈阳航空航天大学学报. 2019(04): 43-48 . 百度学术
14.	李云，崔文刚. 精密单点定位技术发展及应用. 科学技术与工程. 2019(27): 1-11 . 百度学术