机载LiDAR点云数据降维与分类的随机森林方法

doi:10.11947/j.AGCS.2018.20170417

摘要/Abstract

摘要： 探索自动化的激光点云分类方法对于三维建模、城市土地分类、DEM制图等应用具有重要作用。考虑到现有的点云分类算法在提取依赖邻域结构的特征参数时面临邻域尺度的选择难、数据维度高、计算复杂，并且缺乏对分类特征参数的重要性评估和选择等问题，本文提出了基于随机森林的机载LiDAR点云数据降维与分类方法。在分析点云数据的高程、回波、强度等属性特征的基础上，提取归一化高度、高度统计量、表面特征、空间分布特征、回波特征及强度特征6大类特征参数，并构建多尺度特征参数，运用随机森林的特征选择算法对分类特征集进行优化，然后进行点云分类。试验结果表明，基于随机森林的特征选择方法可以有效地降低特征维度，并且使得总体分类精度达到94.3%（Kappa系数为0.922），相比于使用全部特征分类和SVM分类方法而言，该方法的总体分类精度均有一定程度的提高；特征的重要性度量结果表明，归一化高度特征在点云分类中所起的作用最大。

关键词: 机载激光雷达, 特征选择, 点云分类, 随机森林

Abstract: Exploring automatic point cloud classification method is of great importance to 3D modeling,city land classification,DEM mapping and etc.To overcome the problem that extracting geometric feature for point cloud classification involved neighbor structure meets the challenge that the optimal neighbor scale parameter,high data dimension and complex computation,lacking efficient feature importance analysis and feature selection strategy,this paper proposed a point cloud classification and dimension reduction method based on random forest.After analyzing the characteristic of elevation,intensity and echo of laser points,this paper extracted a total of 6 feature types like normalized height feature,height statistic feature,surface metric feature,spatial distribution feature,echo feature,intensity feature,then built a multi-scale feature parameter from them.Finally,a supervised classification was conducted using a random forest algorithm to optimal the feature set and choose the best feature set to classify the point cloud.Results indicate that,the overall accuracy of the proposed method is 94.3% (Kappa coefficient is 0.922).The proposed method got an improvement in the overall accuracy when compared with no feature selection strategy and SVM classification strategy; The feature importance analysis indicates that the normalized height is the most important feature for the classification.

Key words: LiDAR, feature selection, point cloud classification, random forest

中图分类号:

P237

熊艳, 高仁强, 徐战亚. 机载LiDAR点云数据降维与分类的随机森林方法[J]. 测绘学报, 2018, 47(4): 508-518.

XIONG Yan, GAO Renqiang, XU Zhanya. Random Forest Method for Dimension Reduction and Point Cloud Classification Based on Airborne LiDAR[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(4): 508-518.

参考文献

[1] 范士俊, 张爱武, 胡少兴, 等. 基于随机森林的机载激光全波形点云数据分类方法[J]. 中国激光, 2013, 40(9):0914001. FAN Shijun, ZHANG Aiwu, HU Shaoxing, et al. A Method of Classification for Airborne Full Waveform LiDAR Data Based on Random Forest[J]. Chinese Journal of Lasers, 2013, 40(9):0914001.
[2] YAN W Y, SHAKER A, EL-ASHMAWY N. Urban Land Cover Classification Using Airborne LiDAR Data:A Review[J]. Remote Sensing of Environment, 2015, 158(3):295-310.
[3] 徐宏根, 王建超, 郑雄伟, 等. 面向对象的植被与建筑物重叠区域的点云分类方法[J]. 国土资源遥感, 2012, 24(2):23-27. XU Honggen, WANG Jianchao, ZHENG Xiongwei, et al. Object-based Point Clouds Classification of the Vegetation and Building Overlapped Area[J]. Remote Sensing for Land & Resources, 2012, 24(2):23-27.
[4] 李峰, 崔希民, 刘小阳, 等. 机载LiDAR点云提取城市道路网的半自动方法[J]. 测绘科学, 2015, 40(2):88-92. LI Feng, CUI Ximin, LIU Xiaoyang, et al. A Semi-automatic Algorithm of Extracting Urban Road Networks from Airborne LiDAR Point Clouds[J]. Science of Surveying and Mapping, 2015, 40(2):88-92.
[5] ANTONARAKIS A S, RICHARDS K S, BRASINGTON J. Object-based Land Cover Classification Using Airborne LiDAR[J]. Remote Sensing of Environment, 2008, 112(6):2988-2998.
[6] IM J, JENSEN J R, HODGSON M E. Object-based Land Cover Classification Using High-posting-density LiDAR Data[J]. GIScience & Remote Sensing, 2008, 45(2):209-228.
[7] ZHOU Weiqi. An Object-based Approach for Urban Land Cover Classification:Integrating LiDAR Height and Intensity Data[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(4):928-931.
[8] 郭波, 黄先锋, 张帆, 等. 顾及空间上下文关系的JointBoost点云分类及特征降维[J]. 测绘学报, 2013, 42(5):715-721. GUO Bo, HUANG Xianfeng, ZHANG Fan, et al. Points Cloud Classification Using JointBoost Combined with Contextual Information for Feature Reduction[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(5):715-721.
[9] 岳冲, 刘昌军, 王晓芳. 基于多尺度维度特征和SVM的高陡边坡点云数据分类算法研究[J]. 武汉大学学报(信息科学版), 2016, 41(7):882-888. YUE Chong, LIU Changjun, WANG Xiaofang. Classification Algorithm for Laser Point Clouds of High-steep Slopes Based on Multi-scale Dimensionality Features and SVM[J]. Geomatics and Information Science of Wuhan University, 2016, 41(7):882-888.
[10] BRODU N, LAGUE D. 3D Terrestrial LiDAR Data Classification of Complex Natural Scenes Using a Multi-scale Dimensionality Criterion:Applications in Geomorphology[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2012, 68(1):121-134.
[11] ZHAO Jiaping, YOU Suya. Road Network Extraction from Airborne LiDAR Data Using Scene Context[C]//2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. Providence, RI, USA:IEEE, 2012:9-16.
[12] 乔纪纲, 刘小平, 张亦汉. 基于LiDAR高度纹理和神经网络的地物分类[J]. 遥感学报, 2011, 15(3):539-553. QIAO Jigang, LIU Xiaoping, ZHANG Yihan. Land Cover Classification Using LiDAR Height Texture and ANNs[J]. Journal of Remote Sensing, 2011, 15(3):539-553.
[13] NIEMEYER J, WEGNER J D, MALLET C, et al. Conditional Random Fields for Urban Scene Classification with Full Waveform LiDAR Data[C]//Proceedings of 2011 ISPRS Conference on Photogrammetric Image Analysis. Munich, Germany:Springer, 2011:233-244.
[14] 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.
[15] CHU H J, WANG C K, KONG S J, et al. Integration of Full-waveform LiDAR and Hyperspectral Data to Enhance Tea and Areca Classification[J]. GIScience & Remote Sensing, 2016, 53(4):542-559.
[16] MALLET C, BRETAR F. Full-waveform Topographic LiDAR:State-of-the-art[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2009, 64(1):1-16.
[17] ZHANG Wuming, QI Jianbo, WAN Peng, et al. An Easy-to-Use Airborne LiDAR Data Filtering Method Based on Cloth Simulation[J]. Remote Sensing, 2016, 8(6):501.
[18] KIM H B, SOHN G. 3D Classification of Power-line Scene from Airborne Laser Scanning Data Using Random Forests[J]. International Archives of Photogrammetry and Remote Sensing, 2010, 38(3A):126-132.
[19] BREIMAN L. Random Forests[J]. Machine Learning, 2001, 45(1):5-32.
[20] 孙杰, 赖祖龙. 利用随机森林的城区机载LiDAR数据特征选择与分类[J]. 武汉大学学报(信息科学版), 2014, 39(11):1310-1313. SUN Jie, LAI Zulong. Airborne LiDAR Feature Selection for Urban Classification Using Random Forests[J]. Geomatics and Information Science of Wuhan University, 2014, 39(11):1310-1313.
[21] 姚登举, 杨静, 詹晓娟. 基于随机森林的特征选择算法[J]. 吉林大学学报(工学版), 2014, 44(1):137-141. YAO Dengju, YANG Jing, ZHAN Xiaojuan. Feature Selection Algorithm Based on Random Forest[J]. Journal of Jilin University (Engineering and Technology Edition), 2014, 44(1):137-141.
[22] THANGAVEL K, PETHALAKSHMI A. Dimensionality Reduction Based on Rough Set Theory:A Review[J]. Applied Soft Computing, 2009, 9(1):1-12.
[23] VO A V, TRUONG-HONG L, LAEFER D F, et al. Octree-based Region Growing for Point Cloud Segmentation[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 104(1):88-100.
[24] ZHANG Kun, QIAO Shiquan, GAO Kai. A New Point Cloud Reconstruction Algorithm Based-on Geometrical Features[C]//Proceedings of the 7th International Conference on Modelling, Identification and Control. Sousse, Tunisia:IEEE, 2015:1-6.
[25] BENTLEY J L. Multidimensional Binary Search Trees Used for Associative Searching[J]. Communications of the ACM, 1975, 18(9):509-517.