-
摘要: 根据建筑物室内墙壁的空间姿态特征, 建立了一种自动绘制室内平面图的点云向量追踪算法。首先截取一定厚度的室内墙体点云并将其投影至水平面, 在投影平面上建立正方形格网, 对投影后的平面点进行分割管理, 并通过八邻域算法对网格内点云进行聚类。然后采用网格重心法对聚类后的点云数据进行抽稀, 并根据邻域内点间距与连线向量夹角大小对抽稀后的点进行追踪排序, 建立追踪方向的向量序列, 结合向量序列中相邻值夹角的突变情况完成不同墙面的点云分割。最后采用最小二乘算法对分割得到的相同墙面点云进行直线拟合, 求取相邻墙体直线的交点, 建立房屋墙体平面投影线段及其空间连接关系, 依序输出墙体投影线段, 完成房屋平面图的绘制并导出DXF格式数据交换文件。通过对某小区建筑物室内扫描数据的分析, 对所提算法进行验证, 结果表明所提算法可准确快速地对室内三维激光扫描点云进行分析处理, 并完成室内建筑物平面图的绘制。Abstract:Objectives According to the spatial attitude characteristics of the indoor walls, a point cloud vector tracking algorithm for automatically drawing the indoor plan was proposed.Methods Firstly, the indoor wall point cloud with a certain thickness was intercepted and projected onto the horizontal plane, and square grids were established on the projection plane. The plane points after projection were segmented and managed, and the point cloud in every grid was clustered by the eight neighborhood algorithm. Then the grid center of gravity method was used to generate sparse points, which were tracked and sorted according to the distance between points in the neighborhood and the angle of connection vector. The vector sequence of tracking direction was established, and the point cloud segmentation of different walls was completed combined with mutation of angle between adjacent values in the vector sequence. Finally, the least squares algorithm was used to fit the line of the same wall point cloud, and the intersection point of the adjacent wall line was obtained.Results The plane projection line segment of the house wall and its spatial connection relationship were established. The wall projection line segment was output in sequence. The drawing of the house plan was completed and the DXF format data exchange file was exported.Conclusions The proposed algorithm was verified by the analysis of indoor scanning data of a residential building. The results show that the proposed algorithm can accurately and quickly analyzed and processed the indoor laser scanning point cloud, and completed the drawing of interior plan.
-
-
![]()
图 14 不同算法对墙体点云的处理结果对比
Figure 14. Processing Results of Wall Point Clouds by Different Algorithms
![]()
图 15 向量追踪算法室内平面图绘制结果
Figure 15. Result of Point Cloud Vector Tracing Algorithm for Drawing Interior Plan
表 1 不同算法绘图效果对比
Table 1 Results Comparison of Different Algorithms
算法 精度/% 召回率/% F1综合评价系数 IEPF算法 95 83 0.88 HT算法 71 100 0.83 向量追踪算法 100 100 1 
下载: 导出CSV
表 2 不同长度的直线识别准确率
Table 2 Line Recognition Accuracy of Different Lengths
墙壁长度/cm 墙壁数量 正确识别数量 正确率/% (5, 15] 18 16 89 (15, 25] 19 19 100 (25, 35] 25 25 100 > 35 28 28 100
下载: 导出CSV
表 3 拐角点位误差统计
Table 3 Statistics of Corner Point Position Errors
点位误差/mm 拐角数量 (0, 1.5] 13 (1.5, 3.0] 26 (3.0, 4.5] 29 (4.5, 10] 10
下载: 导出CSV
-
[1] Weerakoon T, Ishii K, Nassiraei A A F. Geometric Feature Extraction from 2D Laser Range Data for Mobile Robot Navigation[C]//2015 IEEE 10th International Conference on Industrial and Information Systems(ICⅡS), Peradeniya, Sri Lanka, 2015
[2] 危双丰, 刘明蕾, 赵江洪, 等. 利用点云检测室内导航元素的方法综述[J]. 武汉大学学报·信息科学版, 2018, 43(12): 2 003- 2 011 doi: 10.13203/j.whugis20180144 Wei Shuangfeng, Liu Minglei, Zhao Jianghong, et al. A Survey of Methods for Detecting Indoor Navigation Elements from Point Clouds[J]. Geomatics and Information Science of Wuhan University, 2018, 43(12): 2 003-2 011 doi: 10.13203/j.whugis20180144
[3] Nguyen Tien Thanh, 刘修国, 王红平, 等. 基于激光扫描技术的三维模型重建[J]. 激光与光电子学进展, 2011, 48 (8): 112-117 https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ201108016.htm Nguyen Tien Thanh, Liu Xiuguo, Wang Hongping, et al. 3D Model Reconstruction Based on Laser Scanning Technique[J]. Laser & Optoelectronics Progress, 2011, 48(8): 112-117 https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ201108016.htm
[4] 王鹏, 刘如飞, 马新江, 等. 一种车载激光点云中杆目标自动提取方法[J]. 武汉大学学报·信息科学版, 2020, 45 (7): 1 035-1 042 doi: 10.13203/j.whugis20170421 Wang Peng, Liu Rufei, Ma Xinjiang, et al. An Automatic Extraction Method for Pole-Like Objects from Vehicle-Borne Laser Point Cloud[J]. Geomatics and Information Science of Wuhan University, 2020, 45(7): 1 035-1 042 doi: 10.13203/j.whugis20170421
[5] 朱庆, 李世明, 胡翰, 等. 面向三维城市建模的多点云数据融合方法综述[J]. 武汉大学学报·信息科学版, 2018, 43 (12): 1 962-1 971 doi: 10.13203/j.whugis20180109 Zhu Qing, Li Shiming, Hu Han, et al. Multiple Point Clouds Data Fusion Method for 3D City Modeling[J]. Geomatics and Information Science of Wuhan University, 2018, 43(12): 1 962-1 971 doi: 10.13203/j.whugis20180109
[6] Garulli A, Giannitrapani A, Rossi A, et al. Mobile Robot SLAM for Line-Based Environment Representation[C]//44th IEEE Conference on Decision and Control, Seville, Spain, 2005
[7] 满增光, 叶文华, 楼佩煌, 等. 基于自适应阈值的距离图像线段特征提取[J]. 深圳大学学报(理工版), 2011, 28 (6): 483-488 doi: 10.3969/j.issn.1000-2618.2011.06.003 Man Zengguang, Ye Wenhua, Lou Peihuang, et al. Line Feature Extraction Based on Adaptive Threshold in Range Images[J]. Journal of Shenzhen University Science and Engineering, 2011, 28(6): 483-488 doi: 10.3969/j.issn.1000-2618.2011.06.003
[8] Borges G A, Aldon M J. Line Extraction in 2D Range Images for Mobile Robotics[J]. Journal of Intelligent and Robotic Systems, 2004, 40 (3): 267-297 doi: 10.1023/B:JINT.0000038945.55712.65
[9] Vandorpe J, Van Brussel H, Xu H. Exact Dynamic Map Building for a Mobile Robot Using Geometrical Primitives Produced by a 2D Range Finder[C]//IEEE International Conference on Robotics and Automation, Minneapolis, MN, USA, 1996
[10] Borges G A, Aldon M J. A Split-and-Merge Segmentation Algorithm for Line Extraction in 2D Range Images[C]//15th International Conference on Pattern Recognition (ICPR-2000), Barcelona, Spain, 2000
[11] Nguyen V, Gächter S, Martinelli A, et al. A Comparison of Line Extraction Algorithms Using 2D Range Data for Indoor Mobile Robotics[J]. Autonomous Robots, 2007, 23 (2): 97-111 doi: 10.1007/s10514-007-9034-y
[12] Choi Y H, Lee T K, Oh S Y. A Line Feature Based SLAM with Low Grade Range Sensors Using Geometric Constraints and Active Exploration for Mobile Robot[J]. Autonomous Robots, 2008, 24 (1): 13-27 doi: 10.1007/s10514-007-9050-y
[13] 田朋举, 梅文胜, 花向红, 等. 一种基于点云数据快速生成建筑物断面图的方法[J]. 测绘地理信息, 2020, 45 (4): 88-92 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG202004019.htm Tian Pengju, Mei Wensheng, Hua Xianghong, et al. A Method for Generating Building Sectional Drawing Using 3D Laser Point Cloud Data[J]. Journal of Geomatics, 2020, 45(4): 88-92 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG202004019.htm
[14] He X, Cai Z H. Feature Extraction from 2D Laser Range Data for Indoor Navigation of Aerial Robot [C]//2013 Chinese Automation Congress, Changsha, China, 2013
[15] 湛逸飞, 杨必胜. 基于LiDAR点云法向量稳健估计的室内平面图自动生成方法[J]. 地理信息世界, 2017, 24 (1): 92-96 doi: 10.3969/j.issn.1672-1586.2017.01.018 Zhan Yifei, Yang Bisheng. An Automatic Indoor Plan Generation Method Based on Robust LiDAR Point Cloud Normal Estimation[J]. Geomatics World, 2017, 24 (1): 92-96 doi: 10.3969/j.issn.1672-1586.2017.01.018
[16] 郑德华. ICP算法及其在建筑物扫描点云数据配准中的应用[J]. 测绘科学, 2007, 32 (2): 31-32 https://www.cnki.com.cn/Article/CJFDTOTAL-CHKD200702008.htm Zheng Dehua. ICP Algorithm and Application in the Data Registration of Building Scanning Point Cloud [J]. Science of Surveying and Mapping, 2007, 32 (2): 31-32 https://www.cnki.com.cn/Article/CJFDTOTAL-CHKD200702008.htm
[17] 何君. 基于局部拟合平面投影搜索最近点的ICP配准[J]. 测绘地理信息, 2019, 44 (4): 86-89 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG201904021.htm He Jun. ICP Registration Algorithm Based on Closet Point Searching in Local Plane Projection[J]. Journal of Geomatics, 2019, 44(4): 86-89 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG201904021.htm
[18] 屈亚运, 程英蕾, 邱浪波. 改进的八邻域搜索提取建筑物立体特征方法[J]. 空军工程大学学报(自然科学版), 2015, 16 (4): 66-69 https://www.cnki.com.cn/Article/CJFDTOTAL-KJGC201504016.htm Qu Yayun, Cheng Yinglei, Qiu Langbo. An Improved Method of Extracting 3D Features of Buildings Based on Eight Neighborhood Search Method[J]. Journal of Air Force Engineering University(Natural Science Edition), 2015, 16(4): 66-69 https://www.cnki.com.cn/Article/CJFDTOTAL-KJGC201504016.htm
[19] 衡星辰, 罗俊颉, 郭俊文, 等. 八邻域网格聚类的多样性XML文档近似查询算法[J]. 西安交通大学学报, 2007, 41(8): 907-911 https://www.cnki.com.cn/Article/CJFDTOTAL-XAJT200708009.htm Heng Xingchen, Luo Junjie, Guo Junwen, et al. Approximate Query Algorithm Based on EightNeighbor Grid Clustering for Heterogeneous XML Documents[J]. Journal of Xi'an Jiaotong University, 2007, 41(8): 907-911 https://www.cnki.com.cn/Article/CJFDTOTAL-XAJT200708009.htm
[20] 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]. 地球信息科学学报, 2016, 18 (7): 878-885 https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX201607004.htm Peng Chen, Yu Bailang, Wu Bin, et al. 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 https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX201607004.htm
-
期刊类型引用(10)
1. 曾广泉，马韬，张孟希，戴妍，陈凯文，丁继辉，俞双恩，王中文. 基于无人机多光谱影像的不同施氮量水稻LAI反演方法研究. 江苏农业科学. 2024(20): 41-48 . 
百度学术
2. 高钰琪，许桂玲，冯跃华，王晓珂，任红军，由晓璇，韩志丽，李家乐. 基于冠层高光谱植被指数的水稻产量预测模型研究. 中国稻米. 2023(05): 38-44 . 百度学术
3. 彭晓伟，张爱军，王楠，赵丽，杨晓楠. 高光谱技术在土壤及适种作物的研究进展. 遥感信息. 2022(01): 32-39 . 百度学术
4. 王晓珂，刘婷婷，许桂玲，冯跃华，彭金凤，李杰，罗强鑫，韩志丽，卢苇，PHONENASAY Somsana. 基于冠层高光谱遥感的杂交水稻植被指数氮素营养诊断模型. 中国稻米. 2021(03): 21-29 . 百度学术
5. 王浩淼，宋苗语，李翔，扈朝阳，鲁任翔，王翔，马会勤. 无人机高光谱遥感监测葡萄长势与缺株定位. 园艺学报. 2021(08): 1626-1634 . 百度学术
6. 刘雅婷，龚龑，段博，方圣辉，彭漪. 多时相NDVI与丰度综合分析的油菜无人机遥感长势监测. 武汉大学学报(信息科学版). 2020(02): 265-272 . 百度学术
7. 陈晓凯，李粉玲，王玉娜，史博太，侯玉昊，常庆瑞. 无人机高光谱遥感估算冬小麦叶面积指数. 农业工程学报. 2020(22): 40-49 . 百度学术
8. 落莉莉，常庆瑞，武旭梅，杨景，李粉玲，王琦. 夏玉米叶片光合色素含量高光谱估算. 干旱地区农业研究. 2019(04): 178-183 . 百度学术
9. 张良培，刘蓉，杜博. 使用量子优化算法进行高光谱遥感影像处理综述. 武汉大学学报(信息科学版). 2018(12): 1811-1818 . 百度学术
10. 李亚妮，鲁蕾，刘勇. 基于PROSAIL模型的水稻田缨帽三角-叶面积指数模型及其应用. 应用生态学报. 2017(12): 3976-3984 . 百度学术
其他类型引用(17)
计量
- 文章访问数: 1418
- HTML全文浏览量: 415
- PDF下载量: 96
- 被引次数: 27
