结合区域生长及主成分分析的机载LiDAR建筑物点云提取
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Aerial LiDAR Buildings Point Clouds Extraction Combining Region Growing and Principal Component Analysis
  • 作者:王竞雪 ; 洪绍轩
  • 英文作者:WANG Jing-xue;HONG Shao-xuan;School of Geomatics,Liaoning Technology University;Faculty of Geosciences and Environmental Engineering,Southwest Jiaotong University;
  • 关键词:机载LiDAR ; 建筑物提取 ; 区域生长 ; 主成分分析
  • 英文关键词:aerial LiDAR;;buildings extraction;;region growing;;principal component analysis
  • 中文刊名:XXCN
  • 英文刊名:Journal of Signal Processing
  • 机构:辽宁工程技术大学测绘与地理科学学院;西南交通大学地球科学与环境工程学院;
  • 出版日期:2018-09-25
  • 出版单位:信号处理
  • 年:2018
  • 期:v.34;No.229
  • 基金:国家自然科学基金青年基金项目(41101452);; 辽宁省教育厅科学研究一般项目(LJYL010)
  • 语种:中文;
  • 页:XXCN201809010
  • 页数:11
  • CN:09
  • ISSN:11-2406/TN
  • 分类号:82-92
摘要
针对机载LiDAR建筑物点云提取过程中与树木紧邻的建筑物难以提取,已有先滤波后提取算法效率低等问题,提出一种结合区域生长与主成分分析的机载LiDAR建筑物点云提取算法。该算法首先对粗差剔除后的机载LiDAR离散点云构建TIN三角网,依据建筑物边缘点所在三角形的特征提取建筑物边缘点;然后将邻域特征优化后的建筑物边缘点作为种子点进行区域生长得到建筑物点云;最后采用主成分分析对提取结果进行检核,剔除非建筑物点云,在此基础上基于连通性对建筑物点云进行单体化分割,剔除小面积区域,得到最终的建筑物激光脚点数据。实验选取国际摄影测量与遥感协会提供的三组典型区域的LiDAR点云数据进行建筑物提取,并与传统形态学和区域生长两种建筑物点云提取算法进行比较,结果表明本文算法可以实现建筑物点云的高精度提取,且对地形及不同类型屋顶的建筑物具有良好的自适应性,验证了算法的可靠性。
        For the airborne Li DAR buildings point clouds extraction process,it is difficult to extract buildings points adjacent to the trees,and extraction efficiency of the algorithm after filtering is inefficiency. Aiming at those problems,this paper propose an airborns Li DAR buildings points extraction method based on region growing and principal component analysis. Firstly,the proposed altithom uses airborne Li DAR discrete points which are eliminated gross error to construct the TIN triangulation. After that extracting buildings boundary points according to the feature of the boundary triangle. Secondly,the buildings point clouds would be obtained by region growing with seed points which were from buildings boundary points optimized by neighborhood spatial feature. Finally,the extraction results are checked by principal component analysis algorithm,meanwhile the non-buildings point clouds would be filtered out. Point clouds regions are segmented based on building connectivity and small regions are removed,the final buildings laser foot data is obtained. Three typical Li DAR point clouds data,which are provided by the International Society for Photogrammetry and Remote Sensing,are selected for buildings extraction experiments. By comparing with the traditional morphology and region growing point clouds extraction methods,the test results show that the proposed algorithm can achieve high precision buildings point clouds extraction and have good adaptability to terrain and buildings of different roof types. The reliability of the algorithm is verified.
引文
[1]张小红.机载激光雷达测量技术理论与方法[M].武汉:武汉大学出版社,2007.Zhang Xiaohong.Theories,Methods of Airborne Li DARTechni[M].Wuhan:Wuhan University Press,2007.(in Chinese)
    [2]周平华,熊彪.半自动机载Li DAR点云建筑物三维重建方法[J].测绘科学,2017,42(5):128-130.Zhou Pinghua,Xiong Biao.3D reconstruction method of buildings of semi-automatic airborne Li DAR point clouds[J].Science of Surveying and Mapping,2017,42(5):128-130.(in Chinese)
    [3]赵瑞斌,庞明勇,张燕玲,等.机载Li DAR点云中精细建筑物顶面的渐进提取[J].计算机辅助设计与图形学学报,2017,29(4):624-631.Zhao Ruibin,Pang Mingyong,Zhang Yanling,et al.Progressively Extracting Accurate Building Roofs from Airborne Li DAR Data[J].Journal of Computer-Aided Design&Computer Graphics,2017,29(4):624-631.(in Chinese)
    [4]刘修国,张靖,高伟,等.Lidar点云数据中建筑物的快速提取[J].地球科学-中国地质大学学报,2006,31(5):615-618.Liu Xiuguo,Zhang Jing,Gao Wei,et al.Extract Buildings Quickly from Lidar Point Cloud Data[J].Earth Science-Journal of China University of Geosciences,2006,31(5):615-618.(in Chinese)
    [5]徐文学,杨必胜,魏征,等.多标记点过程的Li DAR点云数据建筑物和树冠提取[J].测绘学报,2013,42(1):51-58.Xu Wenxue,Yang Bisheng,Wei Zheng,et al.Buildings and Tree Crown Extraction from Li DAR Point Cloud Data Based on Multi-marked Point Process[J].Acta Geodaetica et Cartographica Sinica,2013,42(1):51-58.(in Chinese)
    [6]张皓,黄艳,杨洋,等.基于GLCM纹理特征的Li DAR点云建筑物自动提取[J].测绘通报,2009(11):31-33.Zhang Hao,Huang Yan,Yang Yang,et al.Automatic Extraction of Buildings from Li DAR Point Clouds Based on GLCM Texture Features[J].Bulletin of Surveying and Mapping,2009(11):31-33.(in Chinese)
    [7]Cao Y,Zhao H,Li N,et al.Land-Cover Classification by Airborne LIDAR Data Fused with Aerial Optical Images[C]∥2011 International Workshop on Multi-Platform/Multi-Sensor Remote Sensing and Mapping,2011:1-6.
    [8]Awrangjeb M,Ravanbakhsh M,Fraser C S.Automatic detection of residential buildings using LIDAR data and multispectral imagery[J].Isprs Journal of Photogrammetry&Remote Sensing,2010,65(5):457-467.
    [9]Wang M,Tseng Y H.Automatic Segmentation of Lidar Data into Coplanar Point Clusters Using an Octree-Based Split-and-Merge Algorithm[J].Photogrammetric Engineering&Remote Sensing,2010,76(4):407-420.
    [10]汪禹芹.机载点云数据的建筑物提取和模型规范化研究[D].南京:南京大学,2013.Wang Yuqin.Research on building extraction and model regularization from aerial Li DAR data[D].Nanjing:Nanjing University,2013.(in Chinese)
    [11]罗胜,姜挺,王鑫,等.原始机载Li DAR点云中建筑物激光点的自动提取[J].测绘科学技术学报,2013,30(3):269-273.Luo Sheng,Jiang Ting,Wang Xin,et al.Automatic Extraction of Building Points from Raw Air Borne Li DARData[J].Journal of Geomatics Science and Technology,2013,30(3):269-273.(in Chinese)
    [12]Pang S,Liu Y,Zuo Z,et al.Combination of Region Growing and TIN Edge Segmentation for Extraction of Geometric Features on Building Facades[J].Geomatics&Information Science of Wuhan University,2015,40(1):102-106.
    [13]何曼芸,程英蕾,聂玉泽,等.综合不规则三角网和区域生长的建筑物提取方法[J].空军工程大学学报:自然科学版,2017,18(3):54-59.He Manyun,Cheng Yinglei,Nie Yuze,et al.A Building Extraction Method on Comprehensive Delaunay TINModels and Region Growing[J].Journal of Air Force Engineering University:Natural Science Edition,2017,18(3):54-59.(in Chinese)
    [14]徐杰,施鹏飞.基于相位一致与区域生长的自然彩色图像分割[J].电子学报,2004,32(7):1203-1205.Xu Jie,Shi Pengfei.Natural Color Image Segmentation Based on Phase Congruency and Region Growing[J].Acta Electronica Sinica,2004,32(7):1203-1205.(in Chinese)
    [15]郭雪.机载Li DAR点云数据滤波方法研究[D].西安:西安电子科技大学,2014.Guo Xue.Study on Airborne Li DAR Point Cloud Data Filtering Method[D].Xi’an:Xidian University,2014.(in Chinese)
    [16]卢学良,童晓冲,张永生,等.城市密集点云的区域生长表面构网改进算法[J].武汉大学学报·信息科学版,2016,41(6):832-837.Lu Xueliang,Tong Xiaochong,Zhang Yongsheng,et al.An Improved Region-Growing Surface Triangulation Algorithm for Urban Dense Point Cloud[J].Geomatics and Information Science of Wuhan University,2016,41(6):832-837.(in Chinese)
    [17]张宁宁,杨英宝,于双,等.基于主成分分析及连通性分析的建筑物Li DAR点云提取技术[J].勘察科学技术,2016(3):36-39.Zhang Ningning,Yang Yingbao,Yu Shuang,et al.Technology of Building Li DAR Points Cloud Extraction Based on Principle Component Analysis and Connectivity Analysis[J].Site Investigation Science and Technology,2016(3):36-39.(in Chinese)
    [18]郭佳.机载Li DAR点云数据滤波及建筑物提取技术研究[D].西安:长安大学,2014.Guo Jia.Study on Data Filtering and Buildings Abstraction of Airborne Li DAR Points Cloud Data[D].Xi’an:Chang’an University,2014.(in Chinese)
    [19]尚大帅.机载Li DAR点云数据滤波与分类技术研究[D].郑州:解放军信息工程大学,2012.Shang Dashuai.Research on Filtering and Classification of Airborne Li DAR Data[D].Zhengzhou:PLA Information Engineering University,2012.(in Chinese)

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700