首页 > 论文 > 激光与光电子学进展 > 56卷 > 16期(pp:161002--1)

基于三角网滤波和支持向量机的点云分类算法

Point Cloud Classification Algorithm Based on IPTD and SVM

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为了提高城区机载激光雷达点云数据分类算法的自动化程度和分类精度,提出一种基于渐进加密三角网和双层支持向量机的点云分类算法。采用渐进加密三角网滤波提取地面点,在地面点的基础上对地物点进行归一化处理。对点云特征有效性进行评估,选取特征向量并用最邻近支持向量机(NN-SVM)对地物点进行分类,实现对城区点云数据的多元分类。利用城区点云数据验证该算法,通过分析分类精度对分类效果进行评价。结果表明,该算法有效提高了点云数据分类精度,实现了对城区点云数据的有效分类。

Abstract

Herein, to improve the automation and accuracy of the airborne LiDAR point cloud data classification algorithm, a classification algorithm for point clouds based on improved progressive triangulated irregular network densification (IPTD) and a double-layer support vector machine (SVM) was proposed; the classification effect of the algorithm on urban point cloud data was tested as follows. The IPTD filter method was used to extract ground points, and ground points were normalized based on ground points. Then, the effectiveness of point cloud features was evaluated to select eigenvectors, and nearest-neighbor SVM (NN-SVM) was used to classify the ground feature points, realizing the multiple classification of the urban point cloud data. Furthermore, the classification algorithm was verified using point cloud data from urban regions, and the classification effect was evaluated by analyzing the classification accuracy. The experimental results show that this algorithm can effectively improve the classification accuracy and classify point cloud data in urban areas.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.161002

所属栏目:图像处理

基金项目:国家自然科学基金(41601436);

收稿日期:2019-01-09

修改稿日期:2019-03-12

网络出版日期:2019-08-01

作者单位    点击查看

释小松:空军工程大学信息与导航学院, 陕西 西安 710077
程英蕾:空军工程大学信息与导航学院, 陕西 西安 710077
赵中阳:空军工程大学信息与导航学院, 陕西 西安 710077
秦先祥:空军工程大学信息与导航学院, 陕西 西安 710077

联系人作者:释小松(shixiaosong321@126.com)

备注:国家自然科学基金(41601436);

【1】Wu J, Liu R, Guo N et al. Aerial LiDAR data classification using weighted support vector machines. Geomatics and Information Science of Wuhan University. 38(1), 1-6(2013).
吴军, 刘荣, 郭宁 等. SVM加权学习下的机载LiDAR数据多元分类研究. 武汉大学学报(信息科学版). 38(1), 1-6(2013).

【2】Axelsson P. Processing of laser scanner data—algorithms and applications. ISPRS Journal of Photogrammetry and Remote Sensing. 54(2/3), 138-147(1999).

【3】Sithole G and Vosselman G. Experimental comparison of filter algorithms for bare-Earth extraction from airborne laser scanning point clouds. ISPRS Journal of Photogrammetry and Remote Sensing. 59(1/2), 85-101(2004).

【4】Kilian J, Haala N and Englich M. Capture and evaluation of airborne laser scanner data. International Archives of Photogrammetry and Remote Sensing. 31, 383-388(1996).

【5】Axelsson P. DEM generation from laser scanner data using adaptive TIN models. International Archives of Photogrammetry and Remote Sensing. 33(4), 110-117(2000).

【6】Huang Z W, Liu F and Hu G W. Improved method for LiDAR point cloud data filtering based on hierarchical pseudo-grid. Acta Optica Sinica. 37(8), (2017).
黄作维, 刘峰, 胡光伟. 基于多尺度虚拟格网的LiDAR点云数据滤波改进方法. 光学学报. 37(8), (2017).

【7】Chen X Y, Yun T, Xue L F et al. Classification of tree species using LiDAR point cloud data. Laser & Optoelectronics Progress. 56(12), (2019).
陈向宇, 云挺, 薛联凤 等. 基于激光雷达点云数据的树种分类研究. 激光与光电子学进展. 56(12), (2019).

【8】Anguelov D, Taskar B, Chatalbashev V et al. Discriminative learning of Markov random fields for segmentation of 3D scan data. [C]∥2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR''05), June 20-25, 2005, San Diego, CA, USA. New York: IEEE. 8624033, (2005).

【9】Xiao Y, Hu S X, Xiao S et al. A fast statistical method of tree information from 3D laser point clouds. Chinese Journal of Lasers. 45(5), (2018).
肖杨, 胡少兴, 肖深 等. 从三维激光点云中快速统计树木信息的方法. 中国激光. 45(5), (2018).

【10】Lodha S K, Kreps E J, Helmbold D P et al. Aerial LiDAR data classification using support vector machines (SVM). [C]∥Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT''06), June 14-16, 2006, Chapel Hill, NC, USA. New York: IEEE. 10285115, (2006).

【11】He M Y, Cheng Y L, Nie Y Z et al. A building extraction method on comprehensive delaunay TIN models and region growing. Journal of Air Force Engineering University(Natural Science Edition). 18(3), 54-59(2017).
何曼芸, 程英蕾, 聂玉泽 等. 综合不规则三角网和区域生长的建筑物提取方法. 空军工程大学学报(自然科学版). 18(3), 54-59(2017).

【12】Zhao X Q, Guo Q H, Su Y J et al. Improved progressive TIN densification filtering algorithm for airborne LiDAR data in forested areas. ISPRS Journal of Photogrammetry and Remote Sensing. 117, 79-91(2016).

【13】Liu Y, Dong L and Gao G F. The machine carries the ground of laser radar data thing classification method and treatment. Geomatics & Spatial Information Technology. 38(12), 108-110(2015).
刘颖, 董理, 高国峰. 机载激光雷达数据的地物分类方法及处理方式. 测绘与空间地理信息. 38(12), 108-110(2015).

【14】Boser B E, Guyon I M and Vapnik V N. A training algorithm for optimal margin classifiers. [C]∥Proceedings of the Fifth Annual Workshop on Computational Learning Theory - COLT ''92, July 27-29, 1992, Pittsburgh, Pennsylvania, USA. New York: ACM. 144-152(1992).

【15】Li H L, Wang C H and Yuan B Z. An improved SVM: NN-SVM. Chinese Journal of Computers. 26(8), 1015-1020(2003).
李红莲, 王春花, 袁保宗. 一种改进的支持向量机NN-SVM. 计算机学报. 26(8), 1015-1020(2003).

【16】Wang X, Luo Y P, Jiang T et al. A new classification method for LIDAR data based on unbalanced support vector machine. [C]∥2011 International Symposium on Image and Data Fusion, August 9-11, 2011, Tengchong, Yunnan, China. New York: IEEE. 12318534, (2011).

【17】Fan S J, Zhang A W, Hu S X et al. A method of classification for airborne full waveform LiDAR data based on random forest. Chinese Journal of Lasers. 40(9), (2013).
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. 中国激光. 40(9), (2013).

【18】Abdelhamid D, Chaouki B M and Abdelmalik T A. A new approach to multi-class SVM learning based on OC-SVM for huge databases. ∥Abd Manaf A, Zeki A, Zamani M, et al. Informatics engineering and information science. Communications in computer and information science. Berlin, Heidelberg: Springer. 252, 677-690(2011).

【19】Bigdeli B and Samadzadegan F. Classification of LiDAR data based on multi-class SVM. [C]∥The 2010 Canadian Geomatics Conference and Symposium of Commission I, ISPRS Convergence in Geomatics - Shaping Canada''s Competitive Landscape, June 15-18, 2010, Calgary, Alberta, Canada. USA: NASA. (2010).

【20】Lague D, Brodu N and Leroux J. Accurate 3D comparison of complex topography with terrestrial laser scanner: application to the Rangitikei canyon (N-Z). ISPRS Journal of Photogrammetry and Remote Sensing. 82, 10-26(2013).

【21】Yue C, Liu C J and Wang X F. Classification algorithm for laser point clouds of high-steep slopes based on multi-scale dimensionality features and SVM. Geomatics and Information Science of Wuhan University. 41(7), 882-888(2016).
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. 武汉大学学报(信息科学版). 41(7), 882-888(2016).

【22】Xie J Y. SVM based feature selection algorithms for classification Xi''an:. Xidian University. 15-31(2012).
谢娟英. 基于SVM的特征选择方法研究. 西安: 西安电子科技大学. 15-31(2012).

【23】Hsu C W, Chang C C and Lin C J. A practical guide to support vector classification [S.l.: s.n.]. 1-28(2003).

引用该论文

Xiaosong Shi, Yinglei Cheng, Zhongyang Zhao, Xianxiang Qin. Point Cloud Classification Algorithm Based on IPTD and SVM[J]. Laser & Optoelectronics Progress, 2019, 56(16): 161002

释小松, 程英蕾, 赵中阳, 秦先祥. 基于三角网滤波和支持向量机的点云分类算法[J]. 激光与光电子学进展, 2019, 56(16): 161002

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF