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

doi:10.3724/SP.J.1047.2016.00878

地球信息科学学报 ›› 2016, Vol. 18 ›› Issue (7): 878-885.doi: 10.3724/SP.J.1047.2016.00878

• 地球信息科学理论与方法 • 上一篇下一篇

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

彭晨(), 余柏蒗, 吴宾, 吴健平^*()

华东师范大学地理信息科学教育部重点实验室,上海 200241

收稿日期:2015-07-19 修回日期:2015-09-14 出版日期:2016-07-15 发布日期:2016-07-15
通讯作者: 吴健平 E-mail:51130801069@ecnu.cn;jpwu@geo.ecnu.edu.cn
作者简介:
作者简介：彭晨(1992-),男,硕士生,研究方向为城市遥感与GIS开发。E-mail: 51130801069@ecnu.cn
基金资助:
国家自然科学基金项目(41471449);上海市自然科学基金项目(14ZR1412200);中央高校基本科研业务费专项资金项目

A Method for Semiautomated Segmentation of Building Facade from Mobile Laser Scanning Point Cloud Based on Feature Images and SVM

PENG Chen(), YU Bailang, WU Bin, WU Jianping^*()

Key Laboratory of Geographic Information Science, Ministry of Education, East China Normal University, Shanghai 200241, China

Received:2015-07-19 Revised:2015-09-14 Online:2016-07-15 Published:2016-07-15
Contact: WU Jianping E-mail:51130801069@ecnu.cn;jpwu@geo.ecnu.edu.cn

摘要/Abstract

摘要：

建筑物立面是城市地物的重要组成部分,而移动激光扫描是获取城市地物三维信息的重要手段之一。本文提出了一种基于移动激光扫描点云的建筑物立面半自动提取算法。该方法首先构建研究区水平网格;然后计算局部点云几何特征,并且将特征投影到水平网格生成点云特征图像;接着基于支持向量机（Support Vector Machine,SVM）对建筑物立面网格进行粗提取;最后使用网格属性（形状系数、网格面积、最大高程）对粗提取结果进行过滤,并将结果反投影到三维空间中得到精确的建筑物立面。以卡内基梅隆大学的移动激光扫描点云进行试验后表明,本算法能够较好地提取出建筑物立面,提取精度为84%,召回率为90%,数据修正后精度为88%,召回率为91%。通过与现有算法对比,本文提出的算法具有较高精度。

关键词: 移动激光扫描系统, 建筑物立面提取, 点云特征图像, 支持向量机（SVM）

Abstract:

Building facade is an important component of urban street features. Delineating and representing the building facade would benefit the urban building design and planning. As a new mobile mapping system, Mobile Laser Scanning (MLS) allows the quick and cost-effective acquisition of close-range three-dimensional (3D) measurements of urban street objects. This paper presents a semiautomated segmentation method for identifying the building facades from MLS point clouds data. The method consists of three major steps: (1) a horizontal grid system is built for the study area, and the multidimensional geometric features of 3D point clouds data, including the normal vector feature, omni-variance feature, geometric dimensionality of α1, α2 and α3, and eigen-entropy feature, are defined and calculated. Then, a feature image is created after projecting these features to the horizontal grid. (2) Building facades are roughly extracted using Support Vector Machine (SVM). (3) The rough extraction result is filtered according to the characteristics of grid including the shape coefficient, grid′s area, and the largest elevation. Two MLS point cloud datasets of Carnegie Mellon University (CMU) database were used in this study to estimate the feasibility and effectiveness of the method. It was found that this method performs well in extracting the building facades. The precision of the results is 0.88, and its recall rate is 0.90, which is better than some existing methods. Our method provides an effective tool for extracting building facades of streets from MLS point cloud data.

Key words: Mobile Laser Scanning system, building facades, segmentation, feature images, Support Vector Machine (SVM)

彭晨, 余柏蒗, 吴宾, 吴健平. 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]. 地球信息科学学报, 2016, 18(7): 878-885.DOI:10.3724/SP.J.1047.2016.00878

PENG Chen,YU Bailang,WU Bin,WU Jianping. A Method for Semiautomated Segmentation of Building Facade from Mobile Laser Scanning Point Cloud Based on Feature Images and SVM[J]. Journal of Geo-information Science, 2016, 18(7): 878-885.DOI:10.3724/SP.J.1047.2016.00878

图/表 11

图1

表1

图2

图3

表2

图4

表3

图5

表4

图6

图7

参考文献 19

[1]	Haala ., Brenner C.Extraction of buildings and trees in urban environments[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 1999,54(2):130-137. doi: 10.1016/S0924-2716(99)00010-6
[2]	Suveg ., Vosselman G.Reconstruction of 3D building models from aerial images and maps[J]. ISPRS Journal of Photogrammetry and remote sensing, 2004,58(3):202-224.
[3]	Yu ., Liu ., Wu ., et al.Automated derivation of urban building density information using airborne LiDAR data and object-based method[J]. Landscape and Urban Planning, 2010,98(3):210-219. doi: 10.1016/j.landurbplan.2010.08.004
[4]	Demantké ., Mallet ., David ., et al. Dimensionality based scale selection in 3D lidar point clouds [J]. International Archives of Photogrammetry, Remote Sensin. and Spatial Information Science., Laser Scannin., 2011, XXXVIII-5/W12(97-102.
[5]	Lalonde J ., Vandapel ., Huber D ., et al.Natural terrain classification using three-dimensional ladar data for ground robot mobility[J]. Journal of Field Robotics, 2006,23(10):839-861. doi: 10.1002/rob.20134
[6]	Aijazi A ., Checchin ., Trassoudaine L.Segmentation based classification of 3D urban point clouds: A super-voxel based approach with evaluation[J]. Remote Sensing, 2013,5(4):1624-1650. doi: 10.3390/rs5041624
[7]	Lim E ., Suter D.3D terrestrial LIDAR classifications with super-voxels and multi-scale Conditional Random Fields[J]. Computer-Aided Design, 2009,41(10):701-710. doi: 10.1016/j.cad.2009.02.010
[8]	Wu ., Yu ., Yue ., et al.A voxel-based method for automated identification and morphological parameters estimation of individual street trees from mobile laser scanning data[J]. Remote Sensing, 2013,5(2):584-611. doi: 10.3390/rs5020584
[9]	Golovinskiy ., Kim V ., Funkhouser T.Shape-based recognition of 3D point clouds in urban environments[C]. Computer Vision, 2009:2154-2161.
[10]	Serna ., Marcotegui B.Detection, segmentation and classification of 3D urban objects using mathematical morphology and supervised learning[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014,93(7):243-255. doi: 10.1016/j.isprsjprs.2014.03.015
[11]	Zhu ., Zhao ., Liu ., et al.Segmentation and classification of range image from an intelligent vehicle in urban environment[C]. Intelligent Robots and Systems, 2010:1457-1462.
[12]	史文中,李必军,李清泉.基于投影点密度的车载激光扫描距离图像分割方法[J].测绘学报,2005,34(2):95-100. doi: 10.3321/j.issn:1001-1595.2005.02.001
	[ Shi W ., Li B ., Li Q Q.A Method for Segmentation of Range Image Captured by Vehicle-borne Laserscanning Based on the Density of Projected Points[J]. Acta Geodaetica et Cartographica Sinica, 2005,34(2):95-100. ] doi: 10.3321/j.issn:1001-1595.2005.02.001
[13]	吴宾,余柏蒗,岳文辉,等.一种基于车载激光扫描点云数据的单株行道树信息提取方法[J].华东师范大学学报:自然科学版,2013,3(2):38-49. doi: 10.3969/j.issn.1000-5641.2013.02.005
	[ Wu ., Yu B ., Yue W ., et al.Method for identifying individual street trees from the cloud data of the vehicle-borne laser scanning point[J]. Journal of East China Normal University (Natural Science), 2013,3(2):38-49. ] doi: 10.3969/j.issn.1000-5641.2013.02.005
[14]	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.
	[ Yang B ., Wei ., Li Q ., et al.Extracting Complex Building Facades from Mobile Laser Scanning Data[J]. Acta Geodaetica et Cartographica Sinica, 2013,42(3):411-417. ]
[15]	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.
	[ Yang B ., Wei ., Li Q ., et al.A classification-oriented method of feature image generation for vehicle-borne laser scanning point clouds[J]. Acta Geodaetica et Cartographica Sinica, 2010,39(5):540-545. ]
[16]	Yang ., Dong Z.A shape-based segmentation method for mobile laser scanning point clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013,81(7):19-30. doi: 10.1016/j.isprsjprs.2013.04.002
[17]	张学工. 关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42.
	[ Zhang X G.Introduction to statistical learning theory and support vector machines[J]. Acta Autom Atic A Sinica, 2000,26(1):32-42. ]
[18]	Xiong ., Munoz ., Bagnell J ., et al.3-d scene analysis via sequenced predictions over points and regions[C]. Robotics and Automation, 2011:2609-2616.
[19]	Munoz ., Bagnell J ., Vandapel ., et al.Contextual classification with functional max-margin markov networks[C]. Computer Vision and Pattern Recognition, 2009:975-982.

编号	类别	编号	类别	编号	类别	编号	类别
1001	undet	1109	fire_hydrant	1202	ground	1401	wall
1002	linear_misc	1110	post	1203	paved_road	1402	stairs
1003	surf_misc	1111	sign	1205	curb	1408	fence
1101	wire_bundle	1113	bench	1206	walkway	1409	gate
1102	isolated_wire	1114	lamp	1300	foliage	1410	ceiling
1103	utility_pole	1115	traffict_lights	1301	grass	1411	facade_ledge
1104	crossarm	1116	traffic_lights_support	1302	small_trunk	1412	column
1105	support_wire	1117	garbage	1303	large_trunk	1413	mailbox
1106	support_pole	1118	crosswalk_light	1305	thick_branch	1500	human
1107	lamp_support	1119	parking_meter	1306	shrub	1501	vehicle
1108	transformer	1200	load_bearing	1400	facade	9999	legacy

数据集	网格类型	精度/(%)	召回率/(%)
Data-1	建筑物立面网格	90.7	62.6
	非建筑物立面网格	94.7	99.0
Data-2	建筑物立面网格	95.6	41.1
	非建筑物立面网格	94.3	99.8
Data-3	建筑物立面网格	96.1	51.9
	非建筑物立面网格	93.6	99.7

数据集	A/m²	CI	MH/m	精度/(%)	召回率/(%)
Data-1	1.25	0.45	3	81.7	89.4
Data-2	2.75	0.45	3	89.8	90.7
Data-3	1.25	0.45	3	83.6	90.0

计算方法	精度/(%)	召回率/(%)	F1
S3DP	83	93	0.88
M3N	80	92	0.86
LogR	74	87	0.80
本文方法	84	90	0.87
修正后本文方法	88	91	0.90

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

A Method for Semiautomated Segmentation of Building Facade from Mobile Laser Scanning Point Cloud Based on Feature Images and SVM

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 19

相关文章 4

Metrics

本文评价

推荐阅读 0

[1]	杨浩, 孟娜, 王婧, 郑燕, 赵莉. 基于支持向量机的京津冀城市群热环境时空形态模拟[J]. 地球信息科学学报, 2019, 21(2): 190-200.
[2]	罗海峰, 方莉娜, 陈崇成. 车载激光扫描数据路坎点云提取方法[J]. 地球信息科学学报, 2017, 19(7): 861-871.
[3]	李雪轲, 王晋年, 张立福, 杨杭, 刘凯. 面向对象的航空高光谱图像混合分类方法[J]. 地球信息科学学报, 2014, 16(6): 941-948.
[4]	许菡, 孙永华, 李小娟. 遥感影像混合像元的分解——基于加权后验概率的支持向量机分类算法[J]. 地球信息科学学报, 2013, 15(2): 249-254.