利用机载LiDAR点云提取复杂城市建筑物面域
|
摘要
机载LiDAR技术为探测建筑物提供了大量三维点云坐标。为了能从植被中有效识别建筑物面域,首先利用渐进式TIN加密法识别非地面点云,经过移除低于地面3 m的点云和孤立点云后生成非地面点云的二值化格网,依据自定义的分割算子打断建筑物和植被间的可能连接;然后通过区域生成算法以高差阈值来聚类二者的面域,并使用大坡度密度阈值来提取建筑物的面域;最后使用形态学闭算子填充面域孔洞并平滑其边缘。选取3个典型的复杂城市区域进行测试,结果显示,各区域的提取质量与完成率均高于91%,表明该算法能够达到自动识别建筑物的目的。
Airborne LiDAR technology provides large quantities of three-dimensional point clouds coordinates for detecting buildings.To effectively identify the building region from the vegetation,the authors adopt a progressive densification TIN method to filter no-ground points.After removing some point clouds whose height is less than 3m from ground surface and isolated point clouds,a binary grid cell is produced based on no-ground points.Next,defined segmentation operators are used to disconnect the possible link between buildings and vegetation.Two kinds of regions are clustered based on height difference criteria using the region growing method.Then building regions are extracted according to large slope density values.Finally,a morphological closing operator is applied to fill small holes and smooth edges of extracted building regions.Three typical areas with complex urban conditions were selected to test this algorithm.The results show that this algorithm gives a comparative performance with a precision of over 91 percent in quality and completeness.The results also demonstrate that this algorithm can automatically recognize buildings.
Airborne LiDAR technology provides large quantities of three-dimensional point clouds coordinates for detecting buildings.To effectively identify the building region from the vegetation,the authors adopt a progressive densification TIN method to filter no-ground points.After removing some point clouds whose height is less than 3m from ground surface and isolated point clouds,a binary grid cell is produced based on no-ground points.Next,defined segmentation operators are used to disconnect the possible link between buildings and vegetation.Two kinds of regions are clustered based on height difference criteria using the region growing method.Then building regions are extracted according to large slope density values.Finally,a morphological closing operator is applied to fill small holes and smooth edges of extracted building regions.Three typical areas with complex urban conditions were selected to test this algorithm.The results show that this algorithm gives a comparative performance with a precision of over 91 percent in quality and completeness.The results also demonstrate that this algorithm can automatically recognize buildings.
引文
[1]Awrangjeb M,Zhang C,Fraser C S.Improved building detectionusing texture information[C]//International Archives of Photo-grammetry,Remote Sensing and Spatial Information Sciences,2011,38(3/W22):143-148.
[2]成晓倩,樊良新,赵红强.基于图像分割技术的城区机载Li-DAR数据滤波方法[J].国土资源遥感,2012,24(3):29-32.Cheng X Q,Fan L X,Zhao H Q.Filtering of airborne LiDAR datafor cityscapes based on segmentation[J].Remote Sensing for Landand Resources,2012,24(3):29-32.
[3]Zhang K,Yan J,Chen S C.Automatic construction of building foot-prints from airborne LiDAR data[J].IEEE Transactions on Geo-science and Remote Sensing,2006,44(9):2523-2533.
[4]Rottensteiner F,Trinder J,Clode S,et al.Building detection byfusion of airborne laser scanner data and multi-spectral images:Performance evaluation and sensitivity analysis[J].ISPRS Jour-nal of Photogrammetry and Remote Sensing,2007,62(2):135-149.
[5]Khoshelham K,Nedkov S,Nardinocchi C.A comparison of bayes-ian and evidence-based fusion methods for automated buildingdetection in aerial data[C]//International Archives of the Photo-grammetry,Remote Sensing and Spatial Information Sciences,2008,37(B7):1183-1188.
[6]Zhou Q Y,Neumann U.Fast and extensible building modeling fromairborne LiDAR data[C]//Proceedings of the 16th ACM Sigspa-tial International Conference on Advances in Geographic Informa-tion Systems.New York,2008-11-05(07).
[7]Meng X,Wang L,Currit N.Morphology-based building detectionfrom airborne LiDAR data[J].Photogrammetric Engineering andRemote Sensing,2009,75(4):437-442.
[8]Salah M,Trinder J,Shaker A.Evaluation of the self-organizingmap classifier for building detection from LiDAR data and multi-spectral aerial images[J].Journal of Spatial Science,2009,54(2):1-20.
[9]于海洋,程钢,张育民,等.基于LiDAR和航空影像的地震灾害倒塌建筑物信息提取[J].国土资源遥感,2011,23(3):77-81.Yu H Y,Cheng G,Zhang Y M,et al.The detection of earthquake-caused collapsed building information from LiDAR data andaerophotograph[J].Remote Sensing for Land and Resources,2011,23(3):77-81.
[10]李婷,詹庆明,喻亮.基于地物特征提取的车载激光点云数据分类方法[J].国土资源遥感,2012,24(1):17-21.Li T,Zhan Q M,Yu L.A classification method for mobile laserscanning data based on object feature extraction[J].Remote Sens-ing for Land and Resources,2012,24(1):17-21.
[11]Axelsson P E.DEM generation from laser scanner data using adap-tive TIN models[C]//International Archives of Photogrammetry,Remote Sensing and Spatial Information Sciences,2000,33(B4):110-117.
[12]Hermosilla T,Ruiz L A,Recio J A,et al.Evaluation of automaticbuilding detection approaches combining high resolution imagesand LiDAR data[J].Remote Sensing,2011,3(6):1188-1210.
[2]成晓倩,樊良新,赵红强.基于图像分割技术的城区机载Li-DAR数据滤波方法[J].国土资源遥感,2012,24(3):29-32.Cheng X Q,Fan L X,Zhao H Q.Filtering of airborne LiDAR datafor cityscapes based on segmentation[J].Remote Sensing for Landand Resources,2012,24(3):29-32.
[3]Zhang K,Yan J,Chen S C.Automatic construction of building foot-prints from airborne LiDAR data[J].IEEE Transactions on Geo-science and Remote Sensing,2006,44(9):2523-2533.
[4]Rottensteiner F,Trinder J,Clode S,et al.Building detection byfusion of airborne laser scanner data and multi-spectral images:Performance evaluation and sensitivity analysis[J].ISPRS Jour-nal of Photogrammetry and Remote Sensing,2007,62(2):135-149.
[5]Khoshelham K,Nedkov S,Nardinocchi C.A comparison of bayes-ian and evidence-based fusion methods for automated buildingdetection in aerial data[C]//International Archives of the Photo-grammetry,Remote Sensing and Spatial Information Sciences,2008,37(B7):1183-1188.
[6]Zhou Q Y,Neumann U.Fast and extensible building modeling fromairborne LiDAR data[C]//Proceedings of the 16th ACM Sigspa-tial International Conference on Advances in Geographic Informa-tion Systems.New York,2008-11-05(07).
[7]Meng X,Wang L,Currit N.Morphology-based building detectionfrom airborne LiDAR data[J].Photogrammetric Engineering andRemote Sensing,2009,75(4):437-442.
[8]Salah M,Trinder J,Shaker A.Evaluation of the self-organizingmap classifier for building detection from LiDAR data and multi-spectral aerial images[J].Journal of Spatial Science,2009,54(2):1-20.
[9]于海洋,程钢,张育民,等.基于LiDAR和航空影像的地震灾害倒塌建筑物信息提取[J].国土资源遥感,2011,23(3):77-81.Yu H Y,Cheng G,Zhang Y M,et al.The detection of earthquake-caused collapsed building information from LiDAR data andaerophotograph[J].Remote Sensing for Land and Resources,2011,23(3):77-81.
[10]李婷,詹庆明,喻亮.基于地物特征提取的车载激光点云数据分类方法[J].国土资源遥感,2012,24(1):17-21.Li T,Zhan Q M,Yu L.A classification method for mobile laserscanning data based on object feature extraction[J].Remote Sens-ing for Land and Resources,2012,24(1):17-21.
[11]Axelsson P E.DEM generation from laser scanner data using adap-tive TIN models[C]//International Archives of Photogrammetry,Remote Sensing and Spatial Information Sciences,2000,33(B4):110-117.
[12]Hermosilla T,Ruiz L A,Recio J A,et al.Evaluation of automaticbuilding detection approaches combining high resolution imagesand LiDAR data[J].Remote Sensing,2011,3(6):1188-1210.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心