机载多光谱LiDAR数据的地物分类方法

doi:10.11947/j.AGCS.2018.20170512

测绘学报 ›› 2018, Vol. 47 ›› Issue (2): 198-207.doi: 10.11947/j.AGCS.2018.20170512

机载多光谱LiDAR数据的地物分类方法

潘锁艳, 管海燕

南京信息工程大学遥感与测绘工程学院, 江苏南京 210044

收稿日期:2017-09-11 修回日期:2017-12-04 出版日期:2018-02-20 发布日期:2018-03-02
通讯作者: 管海燕 E-mail:guanhy.nj@nuist.edu.cn
作者简介:潘锁艳(1995-),女,硕士生,研究方向为机载激光雷达数据处理。E-mail:pansy_nuist@163.com
基金资助:
国家自然科学基金（41671454）

Object Classification Using Airborne Multispectral LiDAR Data

PAN Suoyan, GUAN Haiyan

School of Remote Sensing & Geomatics Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China

Received:2017-09-11 Revised:2017-12-04 Online:2018-02-20 Published:2018-03-02
Supported by:
The National Natural Science Foundation of China (No. 41671454)

摘要/Abstract

摘要： 机载多光谱LiDAR系统能够快速地获取大范围地表面上地物光谱和几何数据，并能够保证所获取的光谱与空间几何数据在空间和时间上相对完整和一致性。支持向量机（SVM）是一种基于小样本的学习方法，它避开了从归纳到演绎的传统分类过程。因此，本文提出了基于SVM多光谱LiDAR数据的地物目标分类方法。该方法首先将多个独立波段的LiDAR数据融合为单一的、包含多个波段信息的点云数据，然后将融合后的点云内插为距离影像和多光谱影像，最后利用SVM进行多光谱LiDAR数据的地物覆盖分类。通过对加拿大Optech公司的Titan机载多光谱LiDAR数据的试验证明：相对于传统的单波段LiDAR数据，多光谱LiDAR数据可以获得较好的地物分类精度；比较试验发现SVM分类方法适用于多光谱LiDAR数据的地物分类。

关键词: 多光谱LiDAR, SVM, 地物分类, 多光谱LiDAR植被指数

Abstract: Airborne multispectral LiDAR system,which obtains surface geometry and spectral data of objects,simultaneously,has become a fast effective,large-scale spatial data acquisition method.Multispectral LiDAR data are characteristics of completeness and consistency of spectrum and spatial geometric information.Support vector machine (SVM),a machine learning method,is capable of classifying objects based on small samples.Therefore,by means of SVM,this paper performs land cover classification using multispectral LiDAR data. First,all independent point cloud with different wavelengths are merged into a single point cloud,where each pixel contains the three-wavelength spectral information.Next,the merged point cloud is converted into range and intensity images.Finally,land-cover classification is performed by means of SVM.All experiments were conducted on the Optech Titan multispectral LiDAR data,containing three individual point cloud collected by 532 nm,1024 nm,and 1550 nm laser beams.Experimental results demonstrate that ①compared to traditional single-wavelength LiDAR data,multispectral LiDAR data provide a promising solution to land use and land cover applications;②SVM is a feasible method for land cover classification of multispectral LiDAR data.

Key words: multispectral LiDAR, SVM, land-cover classification, multispectral lidar-based vegetation indices

中图分类号:

P237

潘锁艳, 管海燕. 机载多光谱LiDAR数据的地物分类方法[J]. 测绘学报, 2018, 47(2): 198-207.

PAN Suoyan, GUAN Haiyan. Object Classification Using Airborne Multispectral LiDAR Data[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(2): 198-207.

参考文献

[1] 张继贤, 林祥国, 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. DOI:10.11947/j.AGCS.2017.20170345. ZHANG Jixian, LIN Xiangguo, LIANG Xinlian. Advances and Prospects of Information Extraction from Point Clouds[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10):1460-1469. DOI:10.11947/j.AGCS.2017.20170345.
[2] 高广, 马洪超, 张良, 等. 顾及地形断裂线的LiDAR点云滤波方法研究[J]. 武汉大学学报(信息科学版), 2015, 40(4):474-478. GAO Guang, MA Hongchao, ZHANG Liang, et al. A Ground Filtering Algorithm for Airborne LiDAR in Consideration of Terrain Break Lines[J]. Geomatics and Information Science of Wuhan University, 2015, 40(4):474-478.
[3] 张齐勇, 岑敏仪, 周国清, 等. 城区LiDAR点云数据的树木提取[J]. 测绘学报, 2009, 38(4):330-335. DOI:10.3321/j.issn:1001-1595.2009.04.008. ZHANG Qiyong, CEN Minyi, ZHOU Guoqing, et al. Extracting Trees from LiDAR Data in Urban Region[J]. Acta Geodaetica et Cartographica Sinica, 2009, 38(4):330-335. DOI:10.3321/j.issn:1001-1595.2009.04.008.
[4] AZADBAKHT M, FRASER C S, KHOSHELHAM K. Improved Urban Scene Classification Using Full-Waveform LiDAR[J]. Photogrammetric Engineering & Remote Sensing, 2016, 82(12):973-980.
[5] DONG Weihua, LAN Jianhang, LIANG Shunlin, et al. Selection of LiDAR Geometric Features with Adaptive Neighborhood Size for Urban Land Cover Classification[J]. International Journal of Applied Earth Observation and Geoinformation, 2017, 60:99-110.
[6] SHIROWZHAN S, TRINDER J. Building Classification from LiDAR Data for Spatio-temporal Assessment of 3D Urban Developments[J]. Procedia Engineering, 2017, 180:1453-1461.
[7] 李振玉. 基于激光雷达波形和点云数据的建筑物与树木的分类[J]. 黑龙江科技信息, 2015(29):24. LI Zhenyu. Classification of Buildings and Trees Based on LiDAR Waveform and Point Cloud Data[J]. Heilongjiang Science and Technology Information, 2015(29):24.
[8] 吴杭彬. 融合航空影像的机载激光扫描数据分类与特征提取[J]. 测绘学报, 2011, 40(1):134. WU Hangbin. Classification and Feature Extraction of Airborne LiDAR Data Fused with Aerial Image[J]. Acta Geodaetica et Cartographica Sinica, 2011, 40(1):134.
[9] WANG Hongzhou, GLENNIE C. Fusion of Waveform LiDAR Data and Hyperspectral Imagery for Land Cover Classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 108:1-11.
[10] 刘丽娟, 庞勇, 范文义, 等. 机载LiDAR和高光谱融合实现温带天然林树种识别[J]. 遥感学报, 2013, 17(3):679-695. LIU Lijuan, PANG Yong, FANG Wenyi, et al. Fused Airborne LiDAR and Hyperspectral Data for Tree Species Identification in A Natural Temperate Forest[J]. Journal of Remote Sensing, 2013, 17(3):679-695.
[11] 高利鹏, 史文中, 吕志勇, 等. 基于机载LiDAR和高分辨率遥感影像的城市道路网提取[J]. 遥感技术与应用, 2013, 28(4):562-568. GAO Lipeng, SHI Wenzhong, LV Zhiyong, et al. Road Network Extraction Based on Airborne LiDAR and High Resolution Remote Sensing Imagery[J]. Remote Sensing Technology and Application, 2013, 28(4):562-568.
[12] HAMEDIANFAR A, SHAFRI H Z M, MANSOR S, et al. Improving Detailed Rule-based Feature Extraction of Urban Areas from WorldView-2 Image and LiDAR Data[J]. International Journal of Remote Sensing, 2014, 35(5):1876-1899.
[13] PARIS C, BRUZZONE L. A Three-dimensional Model-based Approach to the Estimation of the Tree Top Height by Fusing Low-density LiDAR Data and Very High Resolution Optical Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(1):467-480.
[14] SWATANTRAN A, DUBAYAH R, ROBERTS D, et al. Mapping Biomass and Stress in the Sierra Nevada Using LiDAR and Hyperspectral Data Fusion[J]. Remote Sensing of Environment, 2011, 115(11):2917-2930.
[15] 许传阳, 李建红. 高分辨率遥感影像结合LiDAR数据的面向对象分类方法[J]. 河南理工大学学报(自然科学版), 2015, 34(2):222-225. XU Chuanyang, LI Jianhong. Object-oriented Classification with High Resolution Image and LiDAR Data[J]. Journal of Henan Polytechnic University (Natural Science), 2015, 34(2):222-225.
[16] WANG Chengkai, TSENG Y H, CHU H J. Airborne Dual-wavelength LiDAR Data for Classifying Land Cover[J]. Remote Sensing, 2014, 6(1):700-715.
[17] WALLACE A M, MCCARTHY A, NICHOL C J, et al. Design and Evaluation of Multispectral LiDAR for the Recovery of Arboreal Parameters[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(8):4942-4954.
[18] WALLACE A, NICHOL C, WOODHOUSE I. Recovery of Forest Canopy Parameters by Inversion of Multispectral LiDAR Data[J]. Remote Sensing, 2012, 4(2):509-531.
[19] GONG Wei, SUN Jia, SHI Shuo, et al. Investigating the Potential of Using the Spatial and Spectral Information of Multispectral LiDAR for Object Classification[J]. Sensors, 2015, 15(9):21989-22002.
[20] VAUHKONEN J, HAKALA T, SUOMALAINEN J, et al. Classification of Spruce and Pine Trees Using Active Hyperspectral LiDAR[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(5):1138-1141.
[21] PUTTONEN E, HAKALA T, NEVALAINEN O, et al. Artificial Target Detection with a Hyperspectral LiDAR Over 26-h Measurement[J]. Optical Engineering, 2015, 54(1):013105.
[22] 李新, 程国栋, 卢玲. 空间内插方法比较[J]. 地球科学进展, 2000, 15(3):260-265. LI Xin, CHENG Guodong, LU Ling. Comparison of Spatial Interpolation Methods[J]. Advance in Earth Sciences, 2000, 15(3):260-265.
[23] 郑红军, 周旭, 毕笃彦. 统计学习理论及支持向量机概述[J]. 现代电子技术, 2003(4):59-61. ZHENG Hongjun, ZHOU Xu, BI Duyan. Introduction Statistical Learning Theory and Support Vector Machines[J]. Modern Electronic Technique, 2003(4):59-61.
[24] 施健, 柳钦火, 闻建光, 等. 面向电子政务的全国典型地物波谱数据服务平台设计与实现[J]. 遥感技术与应用, 2011, 26(4):520-526. SHI Jian, LIU Qinhuo, WEN Jianguang, et al. Design and Realization of the Service Platform for Typical Ground Objects Spectrum Data in China Based on E-government[J]. Remote Sensing Technology and Application, 2011, 26(4):520-526.
[25] SRIPADA R P, HEINIGER R W, WHITE J G, et al. Aerial Color Infrared Photography for Determining Early In-Season Nitrogen Requirements in Corn[J]. Agronomy Journal, 2005, 98(4):968-977.
[26] GITELSON A A, MERZLYAK M N. Remote Sensing of Chlorophyll Concentration in Higher Plant Leaves[J]. Advances in Space Research, 1998, 22(5):689-692.
[27] 杨凯歌, 冯学智, 肖鹏峰, 等. 优化子空间SVM集成的高光谱图像分类[J]. 遥感学报, 2016, 20(3):409-419. YANG Kaige, FENG Xuezhi, XIAO Pengfeng, et al. Optimal Subspace Ensemble with SVM for Hyperspectral Image Classification[J]. Journal of Remote Sensing, 2016, 20(3):409-419.
[28] 李清泉, 李必军, 陈静. 激光雷达测量技术及其应用研究[J]. 武汉测绘科技大学学报, 2000, 25(5):387-392. LI Qingquan, LI Bijun, CHEN Jing. Research on Laser Range Scanning and Its Application[J]. Journal of Wuhan Technical University of Surveying and Mapping, 2000, 25(5):387-392.

机载多光谱LiDAR数据的地物分类方法

Object Classification Using Airborne Multispectral LiDAR Data

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

本文评价

[1]	李道纪, 郭海涛, 卢俊, 赵传, 林雨准, 余东行. 遥感影像地物分类多注意力融和U型网络法[J]. 测绘学报, 2020, 49(8): 1051-1064.
[2]	李永强, 李鹏鹏, 董亚涵, 范辉龙. 车载LiDAR点云数据中杆状地物自动提取与分类[J]. 测绘学报, 2020, 49(6): 724-735.
[3]	龚敏霞, 袁赛, 储征伟, 张书亮, 房彩丽. 顾及多空间相似性的地下管线数据匹配[J]. 测绘学报, 2015, 44(12): 1392-1400.
[4]	胡根生陈长春梁栋. 联合云量自动评估和加权支持向量机的Landsat图像云检测[J]. 测绘学报, 2014, 43(8): 848-854.
[5]	黄贤源,翟国君,隋立芬,黄谟涛,欧阳永忠,柴洪洲. LS-SVM算法中优化训练样本对测深异常值剔除的影响[J]. 测绘学报, 2011, 40(1): 22-27.
[6]	郭健张继贤张永红曹银璇 . 多时相MODIS影像土地覆盖分类比较研究[J]. 测绘学报, 2009, 38(1): 0-11.