三维激光扫描点云分类方法研究进展综述
|
摘要
点云(point cloud)为三维空间坐标系下的离散点集,是一种重要的几何数据,能有效表示物体表面信息。随着三维激光扫描技术的快速发展和普及,三维点云的采集变得更加简单便捷。点云分类,即为每个点分配一个语义标记。此外,点云分类作为三维数据处理的关键环节,在三维重建,数字化建模,文物保护等方面具有广泛的应用价值。此次调研围绕不同三维激光扫描点云在数据采集,特征提取这两方面主要工作,展示了点云分类方法的研究现状,并对该领域未来发展趋势进行总结展望。
Point cloud is a set of discrete points in three-dimensional space coordinate system. It's an important geometric data that can effectively represent the surface information of an object. With the rapid development and popularization of3 D laser scanning technology, the acquisition of 3 D point cloud becomes simpler and more convenient. Point cloud classification, is that assign a semantic label to each point. In addition, as a key link of 3 D data processing, point cloud classification has wide application value in 3 D reconstruction, digital modeling and cultural relic protection. The survey briefly introduces the classification methods based on point cloud in two aspects: capturing, feature extraction. Finally, it presented some future perspectives.
Point cloud is a set of discrete points in three-dimensional space coordinate system. It's an important geometric data that can effectively represent the surface information of an object. With the rapid development and popularization of3 D laser scanning technology, the acquisition of 3 D point cloud becomes simpler and more convenient. Point cloud classification, is that assign a semantic label to each point. In addition, as a key link of 3 D data processing, point cloud classification has wide application value in 3 D reconstruction, digital modeling and cultural relic protection. The survey briefly introduces the classification methods based on point cloud in two aspects: capturing, feature extraction. Finally, it presented some future perspectives.
引文
[1]杨必胜,梁福迅,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):1509-1526.
[2]周玉莲.基于法矢信息的点云特征提取技术的研究[D].哈尔滨:哈尔滨工业大学.2012:4-7.
[3]张继贤,林详国,梁欣廉.点云信息提取研究进展和展望[J].测绘学报,2017,46(10):1460-1469.
[4]DemantkéJ,Mallet C,David N,et al.Dimensionality based scale sele-ction in 3D lidar point clouds[C].International Archives of Photogram-metry,Romote Sen-sing and Spatial Informational Sciences,Laser S-canning,2011,XXXVII-I-5/W12(97-102).
[5]Qing Zhu,Yuan Li,Han Hu,Bo Wu.Robust point cloud classification based on multi-level semantic relationships for urban scenes[J].ISPRS Journal of Photo-grammetry and Remote Sensing,2017,129:86-102.
[6]Martin Weinmann,Boris Jutzi,Stefan Hinz,Clément Mallet.Semantic point cloud interpretation based on optimal neighborhoods,relevant features and efficient classifiers.ISPRS Journal of Photogrammetry a-nd Remote Sensing[J].2015,105(286-304).
[7]Maarten Bassier,Bjorn Van Genechten,Maarten Vergauwen.Classi-fication of sensor independent point cloud data of building objects using random forests[J].Journal of Building Engineering.2018
[8]Liqiang Zhang,Zhuqiang Li,Anjian Li,Fangyu Liu.Large-scale urban point cloud labeling and reconstruction[J].ISPRS Journal of Photo-grammetry and Remote Sensing.2018:86-100.
[9]Mohammed Yousefhussien,David J.Kelbe,Emmett J.Ientilucci,Carl Salvaggio.A multi-scale fully convolutional network for semantic lab-eling of 3D point clouds[J].ISPRS Journal of Photogrammetry and Re-mote Sensing.2018.
[10]李海亭,肖建华,李艳红等.机器学习在车载激光点云分类中的应用研究[J].华中师范大学学报,2015,49(3):460-464.
[11]龚亮.机载Li DAR点云数据分类技术研究[D].河南:解放军信息工程大学2011:15-17.
[12]CHUA C S,JARVIS R.Point Signatures:A New Representation for 3D object Recognition[J].International Journal of Computer Vision,19-97,25(1):63-85.
[13]Andrew E.Johnson,Martial Hebert.Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes[J].IEEETransaction on P-attern Analysis and Machine Intelligence,1999,21(5):433-449.
[14]杨必胜,魏征,李清泉,等.面向车载激光扫描点云快速分类的点云特征图像生成方法[J].测绘学报,2010,39(5):540-545.
[15]董震,杨必胜.车载激光扫描数据中多类目标的层次化提取方法[J].测绘学报,2015,44(9):980-987.
[16]孙杰,赖祖龙.利用随机森林的城区机载Li DAR数据特征选择与分类[J].武汉大学学报,2014,39(11):1310-1313.
[17]彭晨,余柏蒗,吴宾,等.基于移动激光扫描点云特征图像和SVM的建筑物立面半自动提取方法[J].地球信息科学,2016,18(7):878-885.
[18]C.R.Qi,H.Su,K.Mo,and L.J.Guibas.PointNet:Deep learning on points sets for 3d classification and segmentation[C].CoRR,abs/16 12.00593,2016.3,8.
[19]C.R.Qi,L.Yi,H.Su,and L.J.Guibas.PointNet++:Deep hierarchical lear-ning on point sets in a metric space[C].CoRR,abs/16 12.00593,201-6.3.8.
[20]Roman Klokov and Victor Lempisity.Escape from cells:Deep kd-net-works for the recognition of 3d point cloud models[C].ar Xiv:1704.01222,2017.
[21]Yang yan Li,Rui Bu,Mingchao Sun and Baoquan Chen.PointC-NN[C].CVPR,ar Xiv:1801.07791,2018.1.26.
[22]李海亭,肖建华,李艳红,等.机器学习在车载激光点云分类中的应用研究[J].华中师范大学学报,2015,49(3):460-464.
[23]姚吉利,贾象阳,马宁,等.地面激光扫描多站点云整体定向平差模型[J].测绘学报,2014,43(8):835-841.
[24]喻亮.基于车载激光扫描数据的地物分类和快速建模技术研究[D].武汉:武汉大学,2011:1-2.
[25]M.Weinmann,S.Urban,S.Hinz,B.Jutzi and C.Mallet.Distinctive 2D and 3D features for automated large-scale scene analysis in urban areas[J].Computers&Graphics.2015,49:47-57.
[26]Heungsilk B.Kim and Gunho Sohn.Point-based Classification of Pow-er Line Corridor Scene Using Random Forests[J].Photogrammetric Engineering&Remote Sensing.2013,79(9):821-833.
[27]Maarten Bassier,Bjorn Van Genechten,Maarten Vergauwen.Classi-fication of sensor independent point cloud data of building objects u-sing random forests[J].Journal of Building Engineering.2018:2352-7102.
[28]Timo Hackel,Jan D.Wegner,Konrad Schindler.Joint classification and contour extraction of large 3D point clouds[J].ISPRSJournal of Photogrammetry and Remote Sensing.2017,130:231-245.
[29]杨必胜,董震,魏征,等.从车载激光扫描数据中提取复杂建筑物立面的方法[J].测绘学报,2013,42(3):411-417.
[30]王鹏,刘如飞,马新江.车载激光点云中杆状目标自动提取[J].遥感信息,2017(5):52-56.
[2]周玉莲.基于法矢信息的点云特征提取技术的研究[D].哈尔滨:哈尔滨工业大学.2012:4-7.
[3]张继贤,林详国,梁欣廉.点云信息提取研究进展和展望[J].测绘学报,2017,46(10):1460-1469.
[4]DemantkéJ,Mallet C,David N,et al.Dimensionality based scale sele-ction in 3D lidar point clouds[C].International Archives of Photogram-metry,Romote Sen-sing and Spatial Informational Sciences,Laser S-canning,2011,XXXVII-I-5/W12(97-102).
[5]Qing Zhu,Yuan Li,Han Hu,Bo Wu.Robust point cloud classification based on multi-level semantic relationships for urban scenes[J].ISPRS Journal of Photo-grammetry and Remote Sensing,2017,129:86-102.
[6]Martin Weinmann,Boris Jutzi,Stefan Hinz,Clément Mallet.Semantic point cloud interpretation based on optimal neighborhoods,relevant features and efficient classifiers.ISPRS Journal of Photogrammetry a-nd Remote Sensing[J].2015,105(286-304).
[7]Maarten Bassier,Bjorn Van Genechten,Maarten Vergauwen.Classi-fication of sensor independent point cloud data of building objects using random forests[J].Journal of Building Engineering.2018
[8]Liqiang Zhang,Zhuqiang Li,Anjian Li,Fangyu Liu.Large-scale urban point cloud labeling and reconstruction[J].ISPRS Journal of Photo-grammetry and Remote Sensing.2018:86-100.
[9]Mohammed Yousefhussien,David J.Kelbe,Emmett J.Ientilucci,Carl Salvaggio.A multi-scale fully convolutional network for semantic lab-eling of 3D point clouds[J].ISPRS Journal of Photogrammetry and Re-mote Sensing.2018.
[10]李海亭,肖建华,李艳红等.机器学习在车载激光点云分类中的应用研究[J].华中师范大学学报,2015,49(3):460-464.
[11]龚亮.机载Li DAR点云数据分类技术研究[D].河南:解放军信息工程大学2011:15-17.
[12]CHUA C S,JARVIS R.Point Signatures:A New Representation for 3D object Recognition[J].International Journal of Computer Vision,19-97,25(1):63-85.
[13]Andrew E.Johnson,Martial Hebert.Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes[J].IEEETransaction on P-attern Analysis and Machine Intelligence,1999,21(5):433-449.
[14]杨必胜,魏征,李清泉,等.面向车载激光扫描点云快速分类的点云特征图像生成方法[J].测绘学报,2010,39(5):540-545.
[15]董震,杨必胜.车载激光扫描数据中多类目标的层次化提取方法[J].测绘学报,2015,44(9):980-987.
[16]孙杰,赖祖龙.利用随机森林的城区机载Li DAR数据特征选择与分类[J].武汉大学学报,2014,39(11):1310-1313.
[17]彭晨,余柏蒗,吴宾,等.基于移动激光扫描点云特征图像和SVM的建筑物立面半自动提取方法[J].地球信息科学,2016,18(7):878-885.
[18]C.R.Qi,H.Su,K.Mo,and L.J.Guibas.PointNet:Deep learning on points sets for 3d classification and segmentation[C].CoRR,abs/16 12.00593,2016.3,8.
[19]C.R.Qi,L.Yi,H.Su,and L.J.Guibas.PointNet++:Deep hierarchical lear-ning on point sets in a metric space[C].CoRR,abs/16 12.00593,201-6.3.8.
[20]Roman Klokov and Victor Lempisity.Escape from cells:Deep kd-net-works for the recognition of 3d point cloud models[C].ar Xiv:1704.01222,2017.
[21]Yang yan Li,Rui Bu,Mingchao Sun and Baoquan Chen.PointC-NN[C].CVPR,ar Xiv:1801.07791,2018.1.26.
[22]李海亭,肖建华,李艳红,等.机器学习在车载激光点云分类中的应用研究[J].华中师范大学学报,2015,49(3):460-464.
[23]姚吉利,贾象阳,马宁,等.地面激光扫描多站点云整体定向平差模型[J].测绘学报,2014,43(8):835-841.
[24]喻亮.基于车载激光扫描数据的地物分类和快速建模技术研究[D].武汉:武汉大学,2011:1-2.
[25]M.Weinmann,S.Urban,S.Hinz,B.Jutzi and C.Mallet.Distinctive 2D and 3D features for automated large-scale scene analysis in urban areas[J].Computers&Graphics.2015,49:47-57.
[26]Heungsilk B.Kim and Gunho Sohn.Point-based Classification of Pow-er Line Corridor Scene Using Random Forests[J].Photogrammetric Engineering&Remote Sensing.2013,79(9):821-833.
[27]Maarten Bassier,Bjorn Van Genechten,Maarten Vergauwen.Classi-fication of sensor independent point cloud data of building objects u-sing random forests[J].Journal of Building Engineering.2018:2352-7102.
[28]Timo Hackel,Jan D.Wegner,Konrad Schindler.Joint classification and contour extraction of large 3D point clouds[J].ISPRSJournal of Photogrammetry and Remote Sensing.2017,130:231-245.
[29]杨必胜,董震,魏征,等.从车载激光扫描数据中提取复杂建筑物立面的方法[J].测绘学报,2013,42(3):411-417.
[30]王鹏,刘如飞,马新江.车载激光点云中杆状目标自动提取[J].遥感信息,2017(5):52-56.
© 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 |