一种依据点云法向量相似度的结构化道路提取方法

doi:10.13474/j.cnki.11-2246.2018.0352

测绘通报 ›› 2018, Vol. 0 ›› Issue (11): 69-72.doi: 10.13474/j.cnki.11-2246.2018.0352

一种依据点云法向量相似度的结构化道路提取方法

安瑶军¹, 陈晓轩², 隋立春^1,3, 周荣荣¹

1. 长安大学地质工程与测绘学院, 陕西西安 710054;
2. 陕西省交通规划设计研究院, 陕西西安 710065;
3. 地理国情监测国家测绘地理信息局工程技术研究中心, 陕西西安 710064

收稿日期:2018-06-01 修回日期:2018-06-24 出版日期:2018-11-25 发布日期:2018-11-29
作者简介:安瑶军(1993-),男,硕士生,主要研究方向为车载激光扫描数据处理。E-mail:824893600@qq.com
基金资助:
国家自然科学基金（41372330）

A Structural Road Extraction Method Based on Normal Vectors Similarity of Point Clouds

AN Yaojun¹, CHEN Xiaoxuan², SUI Lichun^1,3, ZHOU Rongrong¹

1. College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China;
2. Shaanxi Provincial Transport Planning Design and Research Institute, Xi'an 710065, China;
3. National Administration of Surveying, Mapping and Geoinformation Engineering Research Center of Geographic National Conditions Monitoring, Xi'an 710064, China

Received:2018-06-01 Revised:2018-06-24 Online:2018-11-25 Published:2018-11-29

摘要/Abstract

摘要：

结合结构化道路的点云法向量分布特征，提出了一种依据点云法向量相似度的道路提取方法。首先，对原始点云进行滤波处理，去除非地面点干扰；然后，对滤波后地面点云采用主成分分析法估算出各激光脚点的局部法向量及曲率值；最后，依据点云法向量相似度作为约束条件，采用改进的区域生长算法分割出路面点云。使用两组不同场景下的车载点云数据进行试验，道路提取的完整率与准确率均在93%以上。试验结果表明，该方法提取的道路精度与完整性受路面宽度、形状的影响不大，适用于城镇环境下的结构化道路提取。

关键词: 点云, 道路提取, 主成分分析, 法向量, 区域生长

Abstract:

With the distribution characteristics of point clouds in structural roads, a road extraction method based on similarity of point cloud vector is proposed. The method firstly filters the original point cloud to remove the non-ground point interference, and then uses the principal component analysis method to estimate the local normal vector and the curvature value of each laser foot point after filtering the ground point cloud. As a constraint condition, degree is used to segment the road surface point cloud using an improved region growing algorithm. Using the vehicle point cloud data under two different scenarios to carry out experiments, the completeness and accuracy of road extraction are above 93%. The experimental results show that the accuracy and completeness of the road extracted by this method are not affected by the width and shape of the road. It is applicable to the extraction of structured roads in urban environments.

Key words: point cloud, road extraction, principal component analysis, normal vector, region growing

中图分类号:

安瑶军, 陈晓轩, 隋立春, 周荣荣. 一种依据点云法向量相似度的结构化道路提取方法[J]. 测绘通报, 2018, 0(11): 69-72.

AN Yaojun, CHEN Xiaoxuan, SUI Lichun, ZHOU Rongrong. A Structural Road Extraction Method Based on Normal Vectors Similarity of Point Clouds[J]. 测绘通报, 2018, 0(11): 69-72.

参考文献

[1] PU S, RUTZINGER M, VOSSELMAN G, et al. Recognizing Basic Structures from Mobile Laser Scanning Data for Road Inventory Studies[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2011, 66(6):S28-S39.
[2] 方莉娜, 杨必胜. 车载激光扫描数据的结构化道路自动提取方法[J]. 测绘学报, 2013, 42(2):260-267.
[3] 张达, 李霖, 李游. 基于车载激光扫描的城市道路提取方法[J]. 测绘通报, 2016(7):30-34.
[4] JAAKKOLA A, HYYPPÄ J, HYYPPÄ H, et al. Retrieval Algorithms for Road Surface Modelling Using Laser-based Mobile Mapping[J]. Sensors, 2008, 8(9):5238-5249.
[5] 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.
[6] 魏双全, 房华乐, 林祥国. 先验知识引导的车载激光扫描点云道路信息提取[J]. 测绘科学, 2014, 39(10):81-84.
[7] 闫利, 张毅. 基于法向量模糊聚类的道路面点云数据滤波[J]. 武汉大学学报(信息科学版), 2007, 32(12):1119-1122.
[8] YUAN X, ZHAO C X, CAI Y F, et al. Road-surface Abstraction Using Ladar Sensing[C]//International Conference on Control, Automation, Robotics and Vision.[S.l.]:IEEE, 2009:1097-1102.
[9] SMADJA L, NINOT J, GAVRILOVIC T. Road Extraction and Environment Interpretation from LiDAR Sensors[J]. IAPRS, 2010(38):281-286.
[10] ZHAN Q, YU L. Objects Classification from Laser Scanning Data Based on Multi-class Support Vector Machine[C]//International Conference on Remote Sensing, Environment and Transportation Engineering.[S.l.]:IEEE, 2011:520-523.
[11] ZHANG W, QI J, WAN P, et al. An Easy-to-use Airborne LiDAR Data Filtering Method Based on Cloth Simulation[J]. Remote Sensing, 2016, 8(6):501.
[12] BENTLEY J L. Multidimensional Binary Search Trees Used for Associative Searching[J]. Communications of the ACM, 1975, 18(9):509-517.
[13] HOPPE H. Surface Reconstruction from Unorganized Points[C]//Conference on Computer Graphics and Interactive Techniques.[S.l.]:ACM, 1992:71-78.
[14] RABBANI T, HEUVEL VAV DEN, VOSSELMAN G. Segmentation of Point Clouds Using Smoothness Constraint[J].International Archives of Photogrammetry, Remote Sensing & Spatial Information Sciences,2012,36:38-50.
[15] WANG H, WANG C, CHEN Y, et al. Extracting Road Surface from Mobile Laser Scanning Point Clouds in Large Scale Urban Environment[C]//International Conference on Intelligent Transportation Systems.[S.l.]:IEEE, 2014:2912-2917.

一种依据点云法向量相似度的结构化道路提取方法

A Structural Road Extraction Method Based on Normal Vectors Similarity of Point Clouds

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王艳军, 林云浩, 王书涵, 李少春, 王孟杰. OSM辅助车载LiDAR点云三维道路边界精细提取[J]. 测绘通报, 2022, 0(7): 18-25.
[2]	经皓然, 徐敬海. 异形建筑的无人机点云与地面三维激光扫描点云配准[J]. 测绘通报, 2022, 0(6): 32-39.
[3]	钟少忠, 周克军, 王留召, 毛明楷. 车载点云特征对应影像自动分割技术研究[J]. 测绘通报, 2022, 0(6): 45-48 ,97.
[4]	任月娟, 葛小三. 改进DeepLabV3+网络的遥感影像道路综合提取方法[J]. 测绘通报, 2022, 0(6): 55-61.
[5]	谢洪, 陈立波, 聂倩, 吴玮, 张沛. 利用点云配准的空地影像融合技术[J]. 测绘通报, 2022, 0(6): 82-87.
[6]	谢元, 董梦, 马新建. 多源数据在复杂场景建筑物三维重建的应用[J]. 测绘通报, 2022, 0(6): 143-147.
[7]	李旭. 三维激光扫描技术在地铁隧道竣工测量中的应用[J]. 测绘通报, 2022, 0(6): 166-169.
[8]	谭玉慧, 刘欣怡, 张永军. 超体素约束下的主动再学习LiDAR点云分类框架[J]. 测绘通报, 2022, 0(5): 79-83,100.
[9]	赵立都, 向中富, 周银, 马下平, 张双成, 司梦元, 陈茂霖, 胡川, 潘建平. 利用地面三维激光扫描进行桥梁挠度变形分析[J]. 测绘通报, 2022, 0(5): 95-100.
[10]	王道杰, 陈倍, 孙健辉. 机载LiDAR点云密度对DEM精度的影响[J]. 测绘通报, 2022, 0(5): 140-144,169.
[11]	徐福斌, 曲相屹, 王健, 刘秀涵. 基于LiDAR点云的复杂钢结构模型重建[J]. 测绘通报, 2022, 0(5): 170-173.
[12]	阮明浩, 卢永华, 刘玉贤, 汤圣君, 王伟玺, 张宇琦, 李游. 激光与倾斜点云精确配准与无缝融合[J]. 测绘通报, 2022, 0(4): 6-10.
[13]	张驰, 白志辉, 李亮, 陈冉丽, 吴侃. 利用三维激光扫描技术监测矿区桥梁结构形变[J]. 测绘通报, 2022, 0(4): 122-129.
[14]	许志华, 逯行政, 彭远航, 杨可明, 王宇敏. 依托航空模拟平台的激光雷达技术课程实践教学装备[J]. 测绘通报, 2022, 0(4): 162-166.
[15]	王贝, 叶险峰, 王军宁. 利用点云切片提取技术分析桥梁形变[J]. 测绘通报, 2022, 0(4): 167-171.