Article(id=1322506233530135157, tenantId=1146029695717560320, journalId=1281212831689347082, issueId=1322506166672937516, articleNumber=null, orderNo=null, doi=10.14075/j.jgg.2024.10.462, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1728316800000, receivedDateStr=2024-10-08, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1793239657051, onlineDateStr=2026-10-29, pubDate=1755187200000, pubDateStr=2025-08-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793239657051, onlineIssueDateStr=2026-10-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793239657051, creator=13701087609, updateTime=1793239657051, updator=13701087609, issue=Issue{id=1322506166672937516, tenantId=1146029695717560320, journalId=1281212831689347082, year='2025', volume='45', issue='8', pageStart='771', pageEnd='880', issueExtLink='null', onlineDate='null', pubDate='1755187200000', pubDateStr='2025-08-15', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793239641110, creator='13701087609', updateTime=1793239641110, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=813, endPage=817, ext={EN=ArticleExt(id=1322506233739850358, articleId=1322506233530135157, tenantId=1146029695717560320, journalId=1281212831689347082, language=EN, title=Point Cloud Plane Segmentation Algorithm for Multi-Scale Supervoxel Growth, columnId=null, journalTitle=Journal of Geodesy and Geodynamics, columnName=null, runingTitle=null, highlight=null, articleAbstract=

In order to simultaneously improve the efficiency and reliability of point cloud plane segmentation, based on the multi-scale supervoxel and region growing algorithm, supervoxels are used as the growing units, and the voxel region growing algorithm is used to achieve fine point cloud plane segmentation. The results show that the proposed method has good segmentation effect on both indoor and outdoor point cloud data, which is superior to RANSAC, Khaloo and global energy optimization methods. Moreover, the Precision, Recall and F1-score of the method in this paper are all higher than 0.90.

, authors=Daoxu NIE1, Juanjuan MAO2, *, Xianghong HUA3, Xijiang CHEN2, authorsList=Daoxu NIE, Juanjuan MAO, Xianghong HUA, Xijiang CHEN, authorCompany=null, correspAuthors=Juanjuan MAO, authorNote=

NIE Daoxu, senior engineer, majors in surveying and mapping remote sensing geographic information technology, E-mail:

, correspAuthorsNote=null, copyrightStatement=All rights reserved. Unauthorized reproduction is prohibited., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1322506236860412543, articleId=1322506233530135157, tenantId=1146029695717560320, journalId=1281212831689347082, language=CN, title=多尺度超体素生长的点云平面分割算法, columnId=1322506169105633839, journalTitle=大地测量与地球动力学, columnName=现代大地测量, runingTitle=null, highlight=null, articleAbstract=

为同时提高点云平面分割的效率与可靠性,在基于多尺度超体素及区域生长算法的基础上,以超体素为生长单元,采用体素区域生长算法实现精细点云平面分割。结果表明,本文方法对室内外点云数据都有较好的分割效果,优于RANSAC、Khaloo及全局能量优化方法,且本文方法的Precision、Recall和F1-score都超过0.90。

, authors=聂道许1, 毛娟娟2, *, 花向红3, 陈西江2, authorsList=聂道许, 毛娟娟, 花向红, 陈西江, authorCompany=null, correspAuthors=毛娟娟, authorNote=

聂道许,高级工程师,主要从事测绘遥感地理信息技术研究,E-mail:

, correspAuthorsNote=

毛娟娟,硕士生,主要从事三维激光点云智能分析研究,E-mail:

MAO Juanjuan, postgraduate, majors in three-dimensional laser point cloud intelligent analysis, E-mail:

, copyrightStatement=版权所有,未经授权,不得转载。, copyrightOwner=大地测量与地球动力学编辑部, extLink=null, articleAbsUrl=null, sourceXml=gTt+NUy3Damv6Zqz4swGCw==, magXml=LBYmrrGjv3TQMJnVG199oA==, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=5xp3S9IQuqTVrB6kkBWImg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=gs/HUAHSZWMRQjh913nhAQ==, mapNumber=null, fund=null)}, authors=[Author(id=1322506237682496138, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=253376046@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322506237778965132, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506237682496138, language=EN, stringName=Daoxu NIE, firstName=Daoxu, middleName=null, lastName=NIE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Hunan Remote Sensing Geological Survey and Monitoring Institute, 256 West-Laodong Road, Changsha 410015, China, bio={"content":"

NIE Daoxu, senior engineer, majors in surveying and mapping remote sensing geographic information technology, E-mail:

"}, bioImg=null, bioContent=

NIE Daoxu, senior engineer, majors in surveying and mapping remote sensing geographic information technology, E-mail:

, aboutCorrespAuthor=null), CN=AuthorExt(id=1322506237888017037, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506237682496138, language=CN, stringName=聂道许, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 湖南省遥感地质调查监测所,长沙市劳动西路256号,410015, bio={"content":"

聂道许,高级工程师,主要从事测绘遥感地理信息技术研究,E-mail:

"}, bioImg=null, bioContent=

聂道许,高级工程师,主要从事测绘遥感地理信息技术研究,E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322506237279842944, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, xref=null, ext=[AuthorCompanyExt(id=1322506237305008769, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237279842944, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Hunan Remote Sensing Geological Survey and Monitoring Institute, 256 West-Laodong Road, Changsha 410015, China), AuthorCompanyExt(id=1322506237313397378, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237279842944, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 湖南省遥感地质调查监测所,长沙市劳动西路256号,410015)])]), Author(id=1322506238135480975, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=330672@whut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322506238223561361, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506238135480975, language=EN, stringName=Juanjuan MAO, firstName=Juanjuan, middleName=null, lastName=MAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 School of Safety Science and Emergency Management, Wuhan University of Technology, 205 Luoshi Road, Wuhan 430070, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322506238290670226, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506238135480975, language=CN, stringName=毛娟娟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 武汉理工大学安全科学与应急管理学院,武汉市珞狮路205号,430070, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322506237380506243, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, xref=null, ext=[AuthorCompanyExt(id=1322506237388894852, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237380506243, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Safety Science and Emergency Management, Wuhan University of Technology, 205 Luoshi Road, Wuhan 430070, China), AuthorCompanyExt(id=1322506237397283461, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237380506243, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 武汉理工大学安全科学与应急管理学院,武汉市珞狮路205号,430070)])]), Author(id=1322506238533939860, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322506238617825942, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506238533939860, language=EN, stringName=Xianghong HUA, firstName=Xianghong, middleName=null, lastName=HUA, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 School of Geodesy and Geomatics, Wuhan University, 129 Luoyu Road, Wuhan 430079, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322506238689129111, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506238533939860, language=CN, stringName=花向红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 武汉大学测绘学院,武汉市珞喻路129号,430079, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322506237456003718, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, xref=null, ext=[AuthorCompanyExt(id=1322506237464392327, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237456003718, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 School of Geodesy and Geomatics, Wuhan University, 129 Luoyu Road, Wuhan 430079, China), AuthorCompanyExt(id=1322506237476975240, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237456003718, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 武汉大学测绘学院,武汉市珞喻路129号,430079)])]), Author(id=1322506238789792409, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322506238865289883, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506238789792409, language=EN, stringName=Xijiang CHEN, firstName=Xijiang, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 School of Safety Science and Emergency Management, Wuhan University of Technology, 205 Luoshi Road, Wuhan 430070, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322506238936593052, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506238789792409, language=CN, stringName=陈西江, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 武汉理工大学安全科学与应急管理学院,武汉市珞狮路205号,430070, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322506237380506243, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, xref=null, ext=[AuthorCompanyExt(id=1322506237388894852, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237380506243, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Safety Science and Emergency Management, Wuhan University of Technology, 205 Luoshi Road, Wuhan 430070, China), AuthorCompanyExt(id=1322506237397283461, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237380506243, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 武汉理工大学安全科学与应急管理学院,武汉市珞狮路205号,430070)])])], keywords=[Keyword(id=1322506239028867741, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=EN, orderNo=1, keyword=hypervoxel), Keyword(id=1322506240727560862, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=EN, orderNo=2, keyword=regional growth), Keyword(id=1322506240811446943, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=EN, orderNo=3, keyword=segmentation), Keyword(id=1322506240882750112, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=EN, orderNo=4, keyword=multi-scale), Keyword(id=1322506240945664673, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=EN, orderNo=5, keyword=plane point cloud), Keyword(id=1322506241012773538, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=CN, orderNo=1, keyword=超体素), Keyword(id=1322506241079882403, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=CN, orderNo=2, keyword=区域生长), Keyword(id=1322506241146991268, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=CN, orderNo=3, keyword=分割), Keyword(id=1322506241218294437, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=CN, orderNo=4, keyword=多尺度), Keyword(id=1322506241297986214, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=CN, orderNo=5, keyword=平面点云)], refs=[Reference(id=1322506243592270522, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, doi=null, pmid=null, pmcid=null, year=2010, volume=24, issue=4, pageStart=345, pageEnd=348, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=Rusu R B, journalName=Künstliche Intelligenz, refType=null, unstructuredReference= Rusu R B . Semantic 3D Object Maps for Everyday Manipulation in Human Living Environments[J]. Künstliche Intelligenz, 2010, 24 (4): 345- 348, articleTitle=Semantic 3D Object Maps for Everyday Manipulation in Human Living Environments, refAbstract=null), Reference(id=1322506245202883259, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, doi=null, pmid=null, pmcid=null, year=2017, volume=9, issue=5, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=Li L, Yang F, Zhu H H, journalName=Remote Sensing, refType=null, unstructuredReference= Li L , Yang F , Zhu H H , et al. An Improved RANSAC for 3D Point Cloud Plane Segmentation Based on Normal Distribution Transformation Cells[J]. Remote Sensing, 2017, 9 (5), articleTitle=An Improved RANSAC for 3D Point Cloud Plane Segmentation Based on Normal Distribution Transformation Cells, refAbstract=null), Reference(id=1322506245274186428, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, doi=null, pmid=null, pmcid=null, year=2015, volume=104, issue=null, pageStart=88, pageEnd=100, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=Vo A V, Truong-Hong L, Laefer D F, journalName=ISPRS Journal of Photogrammetry and Remote Sensing, refType=null, unstructuredReference= Vo A V , Truong-Hong L , Laefer D F , et al. Octree-Based Region Growing for Point Cloud Segmentation[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 104, 88- 100, articleTitle=Octree-Based Region Growing for Point Cloud Segmentation, refAbstract=null), Reference(id=1322506245374849725, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, doi=null, pmid=null, pmcid=null, year=2022, volume=33, issue=12, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=Zhao X Y, Li Q Z, Zhang M, journalName=Measurement Science and Technology, refType=null, unstructuredReference= Zhao X Y , Li Q Z , Zhang M , et al. Closely Adjacent Object Segmentation Based on Periphery-Restrictive Region Growing[J]. Measurement Science and Technology, 2022, 33 (12), articleTitle=Closely Adjacent Object Segmentation Based on Periphery-Restrictive Region Growing, refAbstract=null), Reference(id=1322506245437764286, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, doi=10.14075/j.jgg.2021.06.015, pmid=null, pmcid=null, year=2021, volume=41, issue=6, pageStart=633, pageEnd=638, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=周钦坤, 岳建平, 李乐乐, journalName=大地测量与地球动力学, refType=null, unstructuredReference=周钦坤, 岳建平, 李乐乐, 等. 一种分步式建筑物屋顶面点云高精度提取方法[J]. 大地测量与地球动力学, 2021, 41 (6): 633- 638, articleTitle=一种分步式建筑物屋顶面点云高精度提取方法, refAbstract=null), Reference(id=1322506245651673791, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, doi=10.14075/j.jgg.2021.06.015, pmid=null, pmcid=null, year=2021, volume=41, issue=6, pageStart=633, pageEnd=638, url=null, language=null, rfNumber=5, rfOrder=5, authorNames=Zhou Qinkun, Yue Jianping, Li Lele, journalName=null, refType=null, unstructuredReference= Zhou Qinkun , Yue Jianping , Li Lele , et al. A Stepwise High-Precision Extraction for Point Cloud of Building Roof[J]. Journal of Geodesy and Geodynamics, 2021, 41 (6): 633- 638, articleTitle=null, refAbstract=null), Reference(id=1322506245722976960, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, doi=null, pmid=null, pmcid=null, year=2018, volume=137, issue=null, pageStart=112, pageEnd=133, url=null, language=null, rfNumber=6, rfOrder=6, authorNames=Dong Z, Yang B S, Hu P B, journalName=ISPRS Journal of Photogrammetry and Remote Sensing, refType=null, unstructuredReference= Dong Z , Yang B S , Hu P B , 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, articleTitle=An Efficient Global Energy Optimization Approach for Robust 3D Plane Segmentation of Point Clouds, refAbstract=null), Reference(id=1322506245798474433, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Golovinskiy A, Funkhouser T. Min-Cut Based Segmentation of Point Clouds[C]. IEEE 12th International Conference on Computer Vision Workshops, Kyoto, 2009, articleTitle=null, refAbstract=null), Reference(id=1322506245869777602, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Papon J, Abramov A, Schoeler M, et al. Voxel Cloud Connectivity Segmentation-Supervoxels for Point Clouds[C]. 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, 2013, articleTitle=null, refAbstract=null), Reference(id=1322506245945275075, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, doi=null, pmid=null, pmcid=null, year=2018, volume=84, issue=5, pageStart=297, pageEnd=308, url=null, language=null, rfNumber=9, rfOrder=9, authorNames=Hackel T, Wegner J D, Savinov N, journalName=Photogrammetric Engineering and Remote Sensing, refType=null, unstructuredReference= Hackel T , Wegner J D , Savinov N , et al. Large-Scale Supervised Learning for 3D Point Cloud Labeling: Semantic3d.Net[J]. Photogrammetric Engineering and Remote Sensing, 2018, 84 (5): 297- 308, articleTitle=Large-Scale Supervised Learning for 3D Point Cloud Labeling: Semantic3d.Net, refAbstract=null), Reference(id=1322506246121435844, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Charles R Q, Hao S, Mo K C, et al. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 2017, articleTitle=null, refAbstract=null), Reference(id=1322506246205321925, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Yeshwanth C, Liu Y C, Nießner M, et al. ScanNet: A High-Fidelity Dataset of 3D Indoor Scenes[C]. 2023 IEEE/CVF International Conference on Computer Vision, Paris, 2023, articleTitle=null, refAbstract=null), Reference(id=1322506246285013702, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, doi=null, pmid=null, pmcid=null, year=2017, volume=34, issue=null, pageStart=1, pageEnd=16, url=null, language=null, rfNumber=12, rfOrder=12, authorNames=Khaloo A, Lattanzi D, journalName=Advanced Engineering Informatics, refType=null, unstructuredReference= Khaloo A , Lattanzi D . Robust Normal Estimation and Region Growing Segmentation of Infrastructure 3D Point Cloud Models[J]. Advanced Engineering Informatics, 2017, 34, 1- 16, articleTitle=Robust Normal Estimation and Region Growing Segmentation of Infrastructure 3D Point Cloud Models, refAbstract=null)], funds=[Fund(id=1322506242728243892, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, awardId=42171428, language=EN, fundingSource=National Natural Science Foundation of China(42171428), fundOrder=null, country=null), Fund(id=1322506242799547061, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, awardId=42171428, language=CN, fundingSource=国家自然科学基金(42171428), fundOrder=null, country=null), Fund(id=1322506242866655926, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, awardId=62377037, language=EN, fundingSource=National Natural Science Foundation of China(62377037), fundOrder=null, country=null), Fund(id=1322506243160257207, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, awardId=62377037, language=CN, fundingSource=国家自然科学基金(62377037), fundOrder=null, country=null), Fund(id=1322506243235754680, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, awardId=2023AFB950, language=EN, fundingSource=Natural Science Foundation of Hubei Province(2023AFB950), fundOrder=null, country=null), Fund(id=1322506243311252153, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, awardId=2023AFB950, language=CN, fundingSource=湖北省自然科学基金(2023AFB950), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322506237279842944, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, xref=null, ext=[AuthorCompanyExt(id=1322506237305008769, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237279842944, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Hunan Remote Sensing Geological Survey and Monitoring Institute, 256 West-Laodong Road, Changsha 410015, China), AuthorCompanyExt(id=1322506237313397378, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237279842944, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 湖南省遥感地质调查监测所,长沙市劳动西路256号,410015)]), AuthorCompany(id=1322506237380506243, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, xref=null, ext=[AuthorCompanyExt(id=1322506237388894852, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237380506243, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Safety Science and Emergency Management, Wuhan University of Technology, 205 Luoshi Road, Wuhan 430070, China), AuthorCompanyExt(id=1322506237397283461, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237380506243, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 武汉理工大学安全科学与应急管理学院,武汉市珞狮路205号,430070)]), AuthorCompany(id=1322506237456003718, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, xref=null, ext=[AuthorCompanyExt(id=1322506237464392327, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237456003718, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 School of Geodesy and Geomatics, Wuhan University, 129 Luoyu Road, Wuhan 430079, China), AuthorCompanyExt(id=1322506237476975240, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237456003718, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 武汉大学测绘学院,武汉市珞喻路129号,430079)])], figs=[ArticleFig(id=1322506241423815335, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=EN, label=Fig. 1, caption=Division of plane and non-plane after the initial supervoxel segmentation, figureFileSmall=E4pKcvFaeDESbtcy8uQYQg==, figureFileBig=5xp3S9IQuqTVrB6kkBWImg==, tableContent=null), ArticleFig(id=1322506241503507112, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=CN, label=图1, caption=初次超体素分割后的平面和非平面划分, figureFileSmall=E4pKcvFaeDESbtcy8uQYQg==, figureFileBig=5xp3S9IQuqTVrB6kkBWImg==, tableContent=null), ArticleFig(id=1322506241709028009, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=EN, label=Fig. 2, caption=Original point cloud, figureFileSmall=X8W3My+8fSORbpTyLv+hyA==, figureFileBig=fuwLU/rVGvV+p5owZA2CLw==, tableContent=null), ArticleFig(id=1322506241784525482, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=CN, label=图2, caption=原始点云数据, figureFileSmall=X8W3My+8fSORbpTyLv+hyA==, figureFileBig=fuwLU/rVGvV+p5owZA2CLw==, tableContent=null), ArticleFig(id=1322506241872605867, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=EN, label=Fig. 3, caption=Comparison of segmentation results using different methods, figureFileSmall=otlL7rNL88LawO0iyzjz8w==, figureFileBig=Txbc16m5PleEzoYNvCzeLA==, tableContent=null), ArticleFig(id=1322506241931326124, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=CN, label=图3, caption=不同方法分割结果比较, figureFileSmall=otlL7rNL88LawO0iyzjz8w==, figureFileBig=Txbc16m5PleEzoYNvCzeLA==, tableContent=null), ArticleFig(id=1322506242031989421, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=EN, label=Fig. 4, caption=Comparison of segmentation results using different methods, figureFileSmall=56ojaATApbAvIfuqP26GUw==, figureFileBig=OiTKUwIGelphmsxM0XlS6w==, tableContent=null), ArticleFig(id=1322506242099098286, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=CN, label=图4, caption=不同方法分割结果比较, figureFileSmall=56ojaATApbAvIfuqP26GUw==, figureFileBig=OiTKUwIGelphmsxM0XlS6w==, tableContent=null), ArticleFig(id=1322506242187178671, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=EN, label=Tab. 1, caption=

TP, FP, and FN values of four methods

, figureFileSmall=null, figureFileBig=null, tableContent=
RANSAC
方法
Khaloo
方法
全局能量优化
方法
本文
方法
原始点数 453 129
分割后点数 352 392 376 541 383 244 453 037
TP 191 377 289 306 323 547 406 032
FP 42 014 51 541 42 199 21 759
FN 219 011 40 724 35 680 21 333
), ArticleFig(id=1322506242300424880, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=CN, label=表1, caption=

4种方法的TP、FP和FN值

, figureFileSmall=null, figureFileBig=null, tableContent=
RANSAC
方法
Khaloo
方法
全局能量优化
方法
本文
方法
原始点数 453 129
分割后点数 352 392 376 541 383 244 453 037
TP 191 377 289 306 323 547 406 032
FP 42 014 51 541 42 199 21 759
FN 219 011 40 724 35 680 21 333
), ArticleFig(id=1322506242367533745, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=EN, label=Tab. 2, caption=

Precision, Recall and F1-score values of four methods

, figureFileSmall=null, figureFileBig=null, tableContent=
RANSAC
方法
Khaloo
方法
全局能量优化
方法
本文
方法
Precision 0.82 0.85 0.88 0.95
Recall 0.47 0.88 0.90 0.95
F1-score 0.60 0.86 0.89 0.95
), ArticleFig(id=1322506242447225522, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, language=CN, label=表2, caption=

4种方法的Precision、Recall和F1-score值

, figureFileSmall=null, figureFileBig=null, tableContent=
RANSAC
方法
Khaloo
方法
全局能量优化
方法
本文
方法
Precision 0.82 0.85 0.88 0.95
Recall 0.47 0.88 0.90 0.95
F1-score 0.60 0.86 0.89 0.95
)], attaches=null, journal=Journal(id=1281211523964080133, delFlag=0, nameCn=大地测量与地球动力学, nameEn=Journal of Geodesy and Geodynamics, nameHistory1=null, nameHistory2=null, issn=1671-5942, eissn=null, cn=42-1655/P, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=BeWo6OWOseISH6uPOmc2hA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Geodesy and Geodynamics, journalRemark=null, publicationField=null, createdTime=1783394231074, updatedTime=1788951966472, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=D, firstLetterEn=D, subjectCode=Science, subjectName=null, subjectCodeEn=Science, subjectNameEn=null, picCn=BeWo6OWOseISH6uPOmc2hA==, picEn=YHLfVa8gITbOo0FeIjbLDg==, jcr=null, cjcr=null, exts=[JournalExt(id=1304522356412666698, language=CN, name=大地测量与地球动力学, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788951966622, updatedTime=1788951966622, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.jgg09.com/journalx_ddcl/authorLogOn.action, submissionEditorUrl=http://www.jgg09.com/journalx_ddcl/editorLogOn.action, submissionReviewUrl=http://www.jgg09.com/journalx_ddcl/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304522356576244555, language=EN, name=Journal of Geodesy and Geodynamics, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788951966661, updatedTime=1788951966661, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.jgg09.com/journalx_ddcl/authorLogOn.action, submissionEditorUrl=http://www.jgg09.com/journalx_ddcl/editorLogOn.action, submissionReviewUrl=http://www.jgg09.com/journalx_ddcl/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1281212831689347082, websiteList=[Website(id=1281216327125799907, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1281212831689347082, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/ddcl/CN, language=CN, createTime=1783395376235, createBy=18614031015, updateTime=1783395439358, updateBy=18614031015, name=大地测量与地球动力学-中文, tplId=1146099689490845704, title=大地测量与地球动力学, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1281216715371548758, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=articleTextType, value=kx, createTime=1783395468800, updateTime=1783395468800, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715346382931, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=banner, value=null, createTime=1783395468794, updateTime=1783395468794, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715400908889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=grayFlag, value=0, createTime=1783395468807, updateTime=1783395468807, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715333800018, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=logo, value=https://castjournals.cast.org.cn/joweb/ddcl/CN/file/pic?fileId=87adUdwolRb6UqGo0QjlJQ==, createTime=1783395468791, updateTime=1783395468791, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715421880411, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=minRunFlag, value=0, createTime=1783395468812, updateTime=1783395468812, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715363160149, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ddcl/CN/file/pic, createTime=1783395468798, updateTime=1783395468798, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715409297498, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=silenceFlag, value=0, createTime=1783395468809, updateTime=1783395468809, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715358965844, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1783395468797, updateTime=1783395468797, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715384131671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=themeColor, value=null, createTime=1783395468803, updateTime=1783395468803, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715392520280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=themeStyle, value=null, createTime=1783395468805, updateTime=1783395468805, creator=18614031015, updator=18614031015)]), Website(id=1281216327713002474, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1281212831689347082, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/ddcl/EN, language=EN, createTime=1783395376375, createBy=18614031015, updateTime=1783395435863, updateBy=18614031015, name=大地测量与地球动力学-英文, tplId=1146101810881728533, title=Journal of Geodesy and Geodynamics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1281216680483328066, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=articleTextType, value=kx, createTime=1783395460482, updateTime=1783395460483, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680453967935, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=banner, value=null, createTime=1783395460475, updateTime=1783395460475, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680521076805, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=grayFlag, value=0, createTime=1783395460491, updateTime=1783395460491, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680437190718, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=logo, value=https://castjournals.cast.org.cn/joweb/ddcl/EN/file/pic?fileId=87adUdwolRb6UqGo0QjlJQ==, createTime=1783395460471, updateTime=1783395460471, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680542048327, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=minRunFlag, value=0, createTime=1783395460496, updateTime=1783395460496, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680474939457, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ddcl/EN/file/pic, createTime=1783395460480, updateTime=1783395460480, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680533659718, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=silenceFlag, value=0, createTime=1783395460494, updateTime=1783395460494, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680462356544, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1783395460477, updateTime=1783395460477, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680495910979, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=themeColor, value=null, createTime=1783395460485, updateTime=1783395460485, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680508493892, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=themeStyle, value=null, createTime=1783395460488, updateTime=1783395460488, creator=18614031015, updator=18614031015)])], journalTitle=大地测量与地球动力学, weixinUrl=null, journalUrl=http://www.jgg09.com/CN/home, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Geodesy and Geodynamics, journalPhotoCn=BeWo6OWOseISH6uPOmc2hA==, journalPhotoEn=YHLfVa8gITbOo0FeIjbLDg==, journalFirstLetter=D, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/ddcl/CN/10.14075/j.jgg.2024.10.462, detailUrlEn=https://castjournals.cast.org.cn/joweb/ddcl/EN/10.14075/j.jgg.2024.10.462, pdfUrlCn=https://castjournals.cast.org.cn/joweb/ddcl/CN/PDF/10.14075/j.jgg.2024.10.462, pdfUrlEn=https://castjournals.cast.org.cn/joweb/ddcl/EN/PDF/10.14075/j.jgg.2024.10.462, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1755187200000, fullTextJson=null, articleText=null, reference=null)
收藏切换
多尺度超体素生长的点云平面分割算法
收藏切换
聂道许 1 , 毛娟娟 2, * , 花向红 3 , 陈西江 2
大地测量与地球动力学 | 现代大地测量 2025,45(8): 813-817
收起
收藏切换
大地测量与地球动力学 |现代大地测量 2025 , 45 (8) : 813 -817
多尺度超体素生长的点云平面分割算法
全屏
[Author(id=1322506237682496138, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=253376046@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322506237778965132, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506237682496138, language=EN, stringName=Daoxu NIE, firstName=Daoxu, middleName=null, lastName=NIE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Hunan Remote Sensing Geological Survey and Monitoring Institute, 256 West-Laodong Road, Changsha 410015, China, bio={"content":"

NIE Daoxu, senior engineer, majors in surveying and mapping remote sensing geographic information technology, E-mail:

"}, bioImg=null, bioContent=

NIE Daoxu, senior engineer, majors in surveying and mapping remote sensing geographic information technology, E-mail:

, aboutCorrespAuthor=null), CN=AuthorExt(id=1322506237888017037, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506237682496138, language=CN, stringName=聂道许, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 湖南省遥感地质调查监测所,长沙市劳动西路256号,410015, bio={"content":"

聂道许,高级工程师,主要从事测绘遥感地理信息技术研究,E-mail:

"}, bioImg=null, bioContent=

聂道许,高级工程师,主要从事测绘遥感地理信息技术研究,E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322506237279842944, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, xref=null, ext=[AuthorCompanyExt(id=1322506237305008769, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237279842944, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Hunan Remote Sensing Geological Survey and Monitoring Institute, 256 West-Laodong Road, Changsha 410015, China), AuthorCompanyExt(id=1322506237313397378, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237279842944, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 湖南省遥感地质调查监测所,长沙市劳动西路256号,410015)])]), Author(id=1322506238135480975, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=330672@whut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322506238223561361, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506238135480975, language=EN, stringName=Juanjuan MAO, firstName=Juanjuan, middleName=null, lastName=MAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 School of Safety Science and Emergency Management, Wuhan University of Technology, 205 Luoshi Road, Wuhan 430070, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322506238290670226, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506238135480975, language=CN, stringName=毛娟娟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 武汉理工大学安全科学与应急管理学院,武汉市珞狮路205号,430070, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322506237380506243, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, xref=null, ext=[AuthorCompanyExt(id=1322506237388894852, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237380506243, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Safety Science and Emergency Management, Wuhan University of Technology, 205 Luoshi Road, Wuhan 430070, China), AuthorCompanyExt(id=1322506237397283461, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237380506243, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 武汉理工大学安全科学与应急管理学院,武汉市珞狮路205号,430070)])]), Author(id=1322506238533939860, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322506238617825942, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506238533939860, language=EN, stringName=Xianghong HUA, firstName=Xianghong, middleName=null, lastName=HUA, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 School of Geodesy and Geomatics, Wuhan University, 129 Luoyu Road, Wuhan 430079, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322506238689129111, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506238533939860, language=CN, stringName=花向红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 武汉大学测绘学院,武汉市珞喻路129号,430079, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322506237456003718, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, xref=null, ext=[AuthorCompanyExt(id=1322506237464392327, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237456003718, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 School of Geodesy and Geomatics, Wuhan University, 129 Luoyu Road, Wuhan 430079, China), AuthorCompanyExt(id=1322506237476975240, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237456003718, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 武汉大学测绘学院,武汉市珞喻路129号,430079)])]), Author(id=1322506238789792409, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322506238865289883, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506238789792409, language=EN, stringName=Xijiang CHEN, firstName=Xijiang, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 School of Safety Science and Emergency Management, Wuhan University of Technology, 205 Luoshi Road, Wuhan 430070, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322506238936593052, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, authorId=1322506238789792409, language=CN, stringName=陈西江, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 武汉理工大学安全科学与应急管理学院,武汉市珞狮路205号,430070, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322506237380506243, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, xref=null, ext=[AuthorCompanyExt(id=1322506237388894852, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237380506243, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Safety Science and Emergency Management, Wuhan University of Technology, 205 Luoshi Road, Wuhan 430070, China), AuthorCompanyExt(id=1322506237397283461, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506233530135157, companyId=1322506237380506243, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 武汉理工大学安全科学与应急管理学院,武汉市珞狮路205号,430070)])])]
聂道许1 , 毛娟娟2, * , 花向红3, 陈西江2
作者信息
  • 1 湖南省遥感地质调查监测所,长沙市劳动西路256号,410015
  • 2 武汉理工大学安全科学与应急管理学院,武汉市珞狮路205号,430070
  • 3 武汉大学测绘学院,武汉市珞喻路129号,430079
通讯作者:

毛娟娟,硕士生,主要从事三维激光点云智能分析研究,E-mail:

MAO Juanjuan, postgraduate, majors in three-dimensional laser point cloud intelligent analysis, E-mail:

作者简介:

聂道许,高级工程师,主要从事测绘遥感地理信息技术研究,E-mail:

Point Cloud Plane Segmentation Algorithm for Multi-Scale Supervoxel Growth
Daoxu NIE1 , Juanjuan MAO2, * , Xianghong HUA3, Xijiang CHEN2
Affiliations
  • 1 Hunan Remote Sensing Geological Survey and Monitoring Institute, 256 West-Laodong Road, Changsha 410015, China
  • 2 School of Safety Science and Emergency Management, Wuhan University of Technology, 205 Luoshi Road, Wuhan 430070, China
  • 3 School of Geodesy and Geomatics, Wuhan University, 129 Luoyu Road, Wuhan 430079, China
  • NIE Daoxu, senior engineer, majors in surveying and mapping remote sensing geographic information technology, E-mail:

出版时间: 2025-08-15 doi: 10.14075/j.jgg.2024.10.462
文章导航
收藏切换

为同时提高点云平面分割的效率与可靠性,在基于多尺度超体素及区域生长算法的基础上,以超体素为生长单元,采用体素区域生长算法实现精细点云平面分割。结果表明,本文方法对室内外点云数据都有较好的分割效果,优于RANSAC、Khaloo及全局能量优化方法,且本文方法的Precision、Recall和F1-score都超过0.90。

超体素  /  区域生长  /  分割  /  多尺度  /  平面点云

In order to simultaneously improve the efficiency and reliability of point cloud plane segmentation, based on the multi-scale supervoxel and region growing algorithm, supervoxels are used as the growing units, and the voxel region growing algorithm is used to achieve fine point cloud plane segmentation. The results show that the proposed method has good segmentation effect on both indoor and outdoor point cloud data, which is superior to RANSAC, Khaloo and global energy optimization methods. Moreover, the Precision, Recall and F1-score of the method in this paper are all higher than 0.90.

hypervoxel  /  regional growth  /  segmentation  /  multi-scale  /  plane point cloud
聂道许, 毛娟娟, 花向红, 陈西江. 多尺度超体素生长的点云平面分割算法. 大地测量与地球动力学, 2025 , 45 (8) : 813 -817 . DOI: 10.14075/j.jgg.2024.10.462
Daoxu NIE, Juanjuan MAO, Xianghong HUA, Xijiang CHEN. Point Cloud Plane Segmentation Algorithm for Multi-Scale Supervoxel Growth[J]. Journal of Geodesy and Geodynamics, 2025 , 45 (8) : 813 -817 . DOI: 10.14075/j.jgg.2024.10.462
近年来,随着计算机视觉和机器学习的发展,点云平面分割得到国内外学者的广泛关注。现有的点云分割算法主要包括模型拟合[1-2]、区域生长[3-5]和能量优化方法[6-7]。目前大多数点云分割算法依赖于原始数据的空间和视觉特征,如曲率和颜色。然而,这些特征在复杂环境中往往难以全面表达点云的所有信息,导致分割结果易受点云精度及冗余点的影响,从而产生过分割或欠分割的问题。为此,本文通过将超体素作为区域增长单元,结合邻域超体素中位数距离阈值约束,对平面和非平面超体素信息进行细分,并用以超体素为单元的区域生长算法来完成精细的平面分割。该过程不仅可以提高传统点云处理的效率,还能提高分割的准确性。
点云超体素分割是一种基于密度的分割方法,将点云数据划分为多个具有相似特征的区域。本文利用局部信息,无需初始化种子点且不依赖于内部参数的超体素生成算法[8],引入一个明确的能量函数来描述超体素的结构特性。通过基于点云子集的选择来最小化能量函数,从而生成具有优化边界定义的超体素。能量函数可定义为:
$\begin{array}{l}~~~~~~~~~~~~~~~~~\min E(Z) = \\\sum\limits_{i = 1}^{{N^\prime }} {\sum\limits_{j = 1}^{{N^\prime }} {{z_{ij}}} } {D^\prime }\left( {{p_i}, {p_j}} \right) + \lambda \left| {{C^\prime }(Z) - K} \right|\end{array}$
$\text { s. t. } z_{i j}=\{0, 1\}, \forall i, j ; \sum\limits_{j=1}^{N^{\prime}} z_{i j}=1, \forall j$
$D^{\prime}\left(p_i, p_j\right)=1-\left|\boldsymbol{n}_{p_i} \times \boldsymbol{n}_{p_j}\right|+0.4 \frac{\left\|p_i-p_j\right\|}{R}$
$C^{\prime}(Z)=\sum\limits_{i=1}^{N^{\prime}} I\left(\sum\limits_{j=1}^{N^{\prime}} z_{i j}\right)$
$I(x)=\left\{\begin{array}{c}0, x=0 \\1, \text { 其他 }\end{array}\right.$
式中,N′表示点云数量; zij用来限制一个点只能属于一个超体素; D′(pi, pj)表示点与点之间的差异性; C′(Z)表示实际生成超体素的数量; K表示预设生成超体素的数量; npi表示pi点法向量; npj表示pj点法向量; R表示邻域点的距离; I(x)为指示函数。
根据§1.1获得初始超体素后,需要对初始超体素块点云特征进行识别。根据式(6)选取超体素质心点的邻近点数量,选择邻近点数量为kmax与C集合中点数量减1的较小值,可确保在最近邻搜索时邻近点数量不会超过集合中点的总数。该方式可适应超体素点集大小的变化,特别是在点集较小时,能够有效避免错误。
$N=\min \left(k_{\max }, C-1\right)$
式中,N为最近邻近点数量; kmax为最大邻近点数量; C为当前点云簇的点数。
平均距离可表示为:
$D_a=\frac{1}{N} \sum\limits_{i=1}^N d_i$
式中,di为点到超体素块点云拟合平面的距离。
对距离值进行排序,得到d1, d2, …, dN,其中d1≤d2≤…≤dN。计算中位数距离阈值Dt:
$D_t=d(P)$
式中,P为第α百分位数,可表示为:
$P=[\alpha \times N]$
式中,[·]表示向上取整。
根据平均距离Da与阈值Dt的比较结果,点云群集可分为平面或非平面:
$h_s=\left\{\begin{array}{l}\text { planar }, D_a<D_t \\\text { nonplanar }, \text { 其他 }\end{array}\right.$
根据上述步骤可以识别超体素块点云为平面或非平面超体素。将非平面的超体素进一步分割为更小尺度的超体素,重复上述步骤,直到当前尺度小于预定义的最小尺度,最终得到最小尺度和最大数量的平面超体素块点云。同时,也能得到最小尺度和较少数量的非平面超体素块点云。
经过上述处理后,将平面超体素和对应的非平面超体素视为区域生长算法的基本单元。选择曲率最小的超体素作为种子超体素,通过动态调整距离阈值、角度阈值和最小点数等参数,使算法对于不同形状和密度的超体素点云都具有较好的适应性,具体步骤如下:
1) 确定超体素块点云法向量。对于超体素块点云中每个点qi,选择其最近的k个邻点,构成点qi的局部邻域。计算局部邻域内点的均值q:
$\overline{\boldsymbol{q}}=\frac{1}{k} \sum\limits_{j=1}^k \boldsymbol{q}_{i j}$
根据式(12)构建协方差矩阵C:
$\boldsymbol{C}=\frac{1}{k} \sum\limits_{j=1}^k\left(\boldsymbol{q}_{i j}-\overline{\boldsymbol{q}}\right)\left(\boldsymbol{q}_{i j}-\overline{\boldsymbol{q}}\right)^{\mathrm{T}}$
式中,qij为邻域内的点坐标; q为这些点的平均坐标; k为邻近点数量。
对协方差矩阵C进行特征值分解,得到特征值λ1≤λ2≤λ3及其对应的特征向量ν1、ν2、ν3。最小特征值λ1对应的特征向量ν1即为估计的法向量。
为保证法向量的一致性,需要对法向量进行定向。选择一个参考方向r,如视点方向或外部法向量。检查法向量ν1与参考方向r的夹角,如果夹角大于90°,则反转法向量,表达式为:
$\boldsymbol{n}_i=\left\{\begin{array}{l}\boldsymbol{v}_1, \boldsymbol{v}_1 \cdot \boldsymbol{r}>0 \\\boldsymbol{v}_1, \text { 其他 }\end{array}\right.$
将法向量归一化,使其单位化:
$\hat{\boldsymbol{n}}_i=\frac{\boldsymbol{n}_i}{\left\|\boldsymbol{n}_i\right\|}$
2) 超体素块点云曲率计算。曲率是衡量超体素表面弯曲程度的参数,依据3个特征值λ1≤λ2≤λ3得到曲率,表达式为:
$f_p=\frac{\lambda_1}{\lambda_1+\lambda_2+\lambda_2}$
3) 种子点选择。根据曲率值对所有超体素块进行升序排序,选择曲率最小的超体素块作为种子超体素。超体素块曲率较小表明其表面较为平坦,适合作为生长的起始点。初始化分割结果和已访问点集合。
4) 生长过程。从种子超体素开始,依次搜索其最近邻超体素,并根据距离阈值和法线角度阈值进行生长。如果满足生长条件,则将邻近超体素加入种子集合和分割结果,并标记为已访问,从而得到平面超体素的分割结果$\boldsymbol{\varPsi}=\left\{\boldsymbol{S}_1, \boldsymbol{S}_2, \cdots, \boldsymbol{S}_j\right\}$
5) 对于非平面超体素Φ2,得到每个点的曲率f′i及法向量n′i,计算f′i与区域增长每个平面曲率f′j的差值:
$\Delta f_{i j}=f_i^{\prime}-f_j^{\prime}$
计算n′i与区域增长每个平面法向量n′j的夹角:
$\theta_{i j}=\arccos \left(\boldsymbol{n}_i^{\prime} \cdot \boldsymbol{n}_j^{\prime}\right)$
同时计算每个非平面点到每个平面分割数据集最近点的距离dij。
根据式(16)、(17)及距离dij,得到非平面超体素与区域增长平面分割面的融合判断参数:
$C_{i j}=\frac{\Delta f_{i j}}{\max \left(\Delta f_{i j}\right)}+\frac{\theta_{i j}}{\max \left(\theta_{i j}\right)}+\frac{d_{i j}}{\max \left(d_{i j}\right)}$
6) 融合结果。当每个非平面点到平面分割数据集Cij最小时,将其进行融合。
7) 参数设置。根据实际情况调整距离阈值、角度阈值和最小点数等参数,获得满意的效果。
最大邻近点数量kmax和第α百分位数距离的设定会直接影响平面和非平面超体素的分割效果,通过适当调整这2个参数,可以有效避免分割误差。图 1为进行初次超体素分割后,即在最大尺度生成的超体素上进行第1次平面和非平面划分的结果。从图 1(a)可以看出,矩形框内平面区域完全未被划分为平面,而圆形框内非平面区域被错误地划分为平面。主要原因为较小的距离阈值可能导致实际平面中的点被排除,从而增加平面的假阴性率。从图 1(g)、1(h)、1(i)可以看出,矩形框内大部分平面区域被错误地划分为非平面,这是因为较大的距离阈值会忽略点云中精细的几何特征,使得部分较小的、重要的平面区域被忽略或错误地划分为非平面; 而邻近点数量较多会导致算法考虑过多的点,从而可能将本不属于同一平面的点聚在一起,使得平面识别过于泛化,如图 1(i)中圆形框区域。从图 1(d)可以看出,矩形框和圆形框区域都不及图 1(e)划分的平面多; 而图 1(f)中圆形框内非平面区域被错误地划分为平面。因此,当kmax=7,α=0.48时,平面和非平面的初次划分比较合适。从图 1也可以看出,当kmax设置较小时,α也要设置较小,反之亦然。
使用3个基准数据集(Semantic3D.Net[9]、斯坦福大规模3D室内空间数据集S3DIS[10]和ScanNet大规模3D室内场景数据集[11])来评估所提方法的性能。Semantic3D.Net包含40亿个3D点,采集的场所包含农场、市政厅、运动场、城堡和广场,点云数据精度为1 cm。S3DIS为斯坦福大学使用Matterport扫描仪采集的大场景室内3D点云数据集,包含6个教学和办公区域,点云精度达到3 mm。ScanNet数据集由Faro Focus Premium激光扫描仪采集得到,点云精度达到6 mm。上述数据集具有不同的点密度、点位精度和噪声水平,可以很好地评估本文方法的稳健性。同时,这些数据集包含室内和室外点云数据,具有较完整的场景数据,可以很好地评估本文方法的适用场景及普适性。图 2为原始点云数据。
利用本文方法对不同点云数据进行分割,并将分割结果与RANSAC[2]和Khaloo[12]方法进行比较,如图 3、4所示。可以看出,RANSAC方法未对矩形框内区域进行有效分割,如图 3(a)中窗户、屋檐、柱子等区域均与墙体混合在一起,很多区域都出现过分割、欠分割的现象(图 3(d)、3(g)),图 3(j)中部分墙体也被分割成同一面墙,这是因为RANSA方法擅长分割具有明显几何特征的平面,在处理某些几何细节时可能表现不佳。Khaloo方法虽然能对建筑物的主体部分进行较好的分割,但对矩形框区域分割效果不佳,在部分区域也出现欠分割(图 3(b)、3(e)、3(h))和过分割(图 3(k))的现象,这是因为Khaloo方法依赖于初始种子的选取,在面对颜色和纹理变化时,分割效果会有所下降。相对于RANSAC和Khaloo方法,本文方法能够有效地对点云数据进行平面分割,边界保持良好,在细节处理和复杂形状识别上表现最佳。
图 4为第2组点云分别采用RANSAC、Khaloo和本文方法的分割结果。可以看出,RANSAC方法未对该区域进行有效分割,如图 4(a)中墙体、沙发、椅子等分割不够精细,均出现过分割的现象,图 4(d)中矩形框区域以及图 4(g)中左下角和右下角矩形框区域也存在这种情况。这是因为RANSAC方法对参数的选择较为敏感,参数选取不合适会出现过分割或欠分割的现象。Khaloo方法对噪声敏感,导致部分区域被错误分割。该方法对初始种子的选取非常敏感,种子点选择不当会导致分割结果不理想,出现欠分割的现象。本文方法能更准确地分割复杂区域和细节部分,避免过分割现象,提高分割的精确度,并且对噪声具有鲁棒性,不容易误分割出无关的小区域。
为进一步评价分割方法的性能,利用Precision、Recall和F1-score指标来衡量分割的质量。
$\text { Precision }=\frac{|\mathrm{TP}|}{|\mathrm{TP}|+|\mathrm{FP}|}$
$\text { Recall }=\frac{|\mathrm{TP}|}{|\mathrm{TP}|+|\mathrm{FN}|}$
$F_1 \text {-score }=2 \times \frac{\text { Precision } \times \text { Recall }}{\text { Precision }+ \text { Recall }}$
式中,TP表示分割得到的目标面上的点为真实目标面上的点; FP表示非真实目标面上的点被分割成真实目标面上的点; FN表示分割得到的非真实目标面上的点为真实目标面上的点。
提取Semantic3D.Net数据集中部分区域进行分析,采用CloudCompare软件的标记功能,勾选数据中的平面点并添加Label作为评估的真值。将分割结果与真值进行对比,得到TP、FP和FN(表 1)。由表 1可知,4种方法分割后的点数不一致,本文方法分割后保留的点数与实际点数几乎相同,而Khaloo和全局能量优化方法分割后会丢失部分点。原因为这2种方法在分割过程中会将平面点错误地分割成非平面点。虽然Khaloo和全局能量优化方法的TP多于RANSAC方法,但其FP也多于RANSAC方法。本文方法的TP多于其他3种方法,且FP和FN均少于其他3种方法。
表 2为4种方法的Precision、Recall和F1-score值。可以看出,全局能量优化方法的Precision与RANSAC和Khaloo方法相当,均超过0.8,但都低于本文方法的0.95。RANSAC方法的Recall仅为0.47,远低于其他3种方法,主要原因为RANSAC方法将大量真实目标面上的点识别为非真实目标面上的点。RANSAC方法的Recall很低,导致其F1-score也很低,仅为0.60,而Khaloo和全局能量优化方法的F1-score都超过0.80。本文方法的Recall和F1-score都高于Khaloo和全局能量优化方法,且超过0.90。
本文提出基于多尺度超体素分割与区域生长算法相结合的方法,通过优化分割过程和提高分割精度,可以有效解决传统点云分割中的效率和准确性问题。首先采用超体素生成算法对点云进行多尺度划分,不仅可保留点云局部特征,而且能降低数据处理量; 然后利用最近邻方法和中位数距离阈值来优化点的聚合,通过区域生长算法实现精细分割。实验结果表明,本文方法对Semantic3D.Net、S3DIS和ScanNet大规模3D室内外场景数据具有较好的分割效果,优于RANSAC、Khaloo及全局能量优化方法。另外,本文方法分割后能保留绝大部分的原始点云数据,其Precision、Recall和F1-score值都超过0.90,高于其他3种方法。但本文方法涉及的部分参数需要人工调参,如何在达到良好分割效果的基础上自适应调参是下一步研究的方向。
  • 国家自然科学基金(42171428)
  • 国家自然科学基金(62377037)
  • 湖北省自然科学基金(2023AFB950)
参考文献 引证文献
排序方式:
1
Rusu R B . Semantic 3D Object Maps for Everyday Manipulation in Human Living Environments[J]. Künstliche Intelligenz, 2010, 24 (4): 345- 348
2
Li L , Yang F , Zhu H H , et al. An Improved RANSAC for 3D Point Cloud Plane Segmentation Based on Normal Distribution Transformation Cells[J]. Remote Sensing, 2017, 9 (5)
3
Vo A V , Truong-Hong L , Laefer D F , et al. Octree-Based Region Growing for Point Cloud Segmentation[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 104, 88- 100
4
Zhao X Y , Li Q Z , Zhang M , et al. Closely Adjacent Object Segmentation Based on Periphery-Restrictive Region Growing[J]. Measurement Science and Technology, 2022, 33 (12)
5
周钦坤, 岳建平, 李乐乐, 等. 一种分步式建筑物屋顶面点云高精度提取方法[J]. 大地测量与地球动力学, 2021, 41 (6): 633- 638
Zhou Qinkun , Yue Jianping , Li Lele , et al. A Stepwise High-Precision Extraction for Point Cloud of Building Roof[J]. Journal of Geodesy and Geodynamics, 2021, 41 (6): 633- 638
6
Dong Z , Yang B S , Hu P B , 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
7
Golovinskiy A, Funkhouser T. Min-Cut Based Segmentation of Point Clouds[C]. IEEE 12th International Conference on Computer Vision Workshops, Kyoto, 2009
8
Papon J, Abramov A, Schoeler M, et al. Voxel Cloud Connectivity Segmentation-Supervoxels for Point Clouds[C]. 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, 2013
9
Hackel T , Wegner J D , Savinov N , et al. Large-Scale Supervised Learning for 3D Point Cloud Labeling: Semantic3d.Net[J]. Photogrammetric Engineering and Remote Sensing, 2018, 84 (5): 297- 308
10
Charles R Q, Hao S, Mo K C, et al. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 2017
11
Yeshwanth C, Liu Y C, Nießner M, et al. ScanNet: A High-Fidelity Dataset of 3D Indoor Scenes[C]. 2023 IEEE/CVF International Conference on Computer Vision, Paris, 2023
12
Khaloo A , Lattanzi D . Robust Normal Estimation and Region Growing Segmentation of Infrastructure 3D Point Cloud Models[J]. Advanced Engineering Informatics, 2017, 34, 1- 16
2025年第45卷第8期
27
11
引用本文
BibTeX
文章信息
doi: 10.14075/j.jgg.2024.10.462
  • 接收时间:2024-10-08
  • 首发时间:2026-10-29
  • 出版时间:2025-08-15
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-10-08
基金
National Natural Science Foundation of China(42171428)
国家自然科学基金(42171428)
National Natural Science Foundation of China(62377037)
国家自然科学基金(62377037)
Natural Science Foundation of Hubei Province(2023AFB950)
湖北省自然科学基金(2023AFB950)
作者信息
    1 湖南省遥感地质调查监测所,长沙市劳动西路256号,410015
    2 武汉理工大学安全科学与应急管理学院,武汉市珞狮路205号,430070
    3 武汉大学测绘学院,武汉市珞喻路129号,430079

通讯作者:

毛娟娟,硕士生,主要从事三维激光点云智能分析研究,E-mail:

MAO Juanjuan, postgraduate, majors in three-dimensional laser point cloud intelligent analysis, E-mail:

参考文献
分享链接
https://castjournals.cast.org.cn/joweb/ddcl/CN/10.14075/j.jgg.2024.10.462
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏