[an error occurred while processing this directive] 世界地质 2020, 39(2) 479-486 DOI:   10.3969/j.issn.1004-5589.2020.02.024  ISSN: 1004-5589 CN: 22-1111/P
本期目录 | 下期目录 | 过刊浏览 | 高级检索                                                            [打印本页]   [关闭]
测绘·地热
扩展功能
本文信息
Supporting info
PDF(4059KB)
[HTML全文]
参考文献[PDF]
参考文献
服务与反馈
把本文推荐给朋友
加入我的书架
加入引用管理器
引用本文
Email Alert
文章反馈
浏览反馈信息
本文关键词相关文章
三维激光扫描
点云数据
谱聚类算法
Kappa系数
本文作者相关文章
吴翔
王凤艳
林楠
王明常
PubMed
Article by Wu X
Article by Wang F
Article by Lin N
Article by Wang M
基于谱聚类算法的三维激光点云数据分类研究
吴翔1, 王凤艳1, 林楠2, 王明常1
1. 吉林大学地球探测科学与技术学院, 长春 130026;
2. 吉林建筑大学测绘与勘查工程学院, 长春 130018
摘要： 基于Z+F IMAGER 5010C扫描仪采集实验区点云数据，经栅格处理后，结合纹理和形状等信息，采用谱聚类算法对其进行分类，利用混淆矩阵中的Kappa系数对分类结果进行精度评价。通过与传统的K-means算法和高斯混合模型的分类结果进行对比，结果表明：谱聚类算法的分类效果明显，且分类精度较高，且加入纹理和形状信息的分类精度会高于仅含反射强度信息的分类精度，其总体分类精度达到81.36%，Kappa系数达到0.713 8。
关键词： 三维激光扫描   点云数据   谱聚类算法   Kappa系数  
Research on classification of 3D laser point cloud data based on spectral clustering algorithm
WU Xiang1, WANG Feng-yan1, LIN Nan2, WANG Ming-chang1
1. College of Geo-exploration Science and Technology, Jilin University, Changchun 130026, China;
2. College of Surveying and Prospecting Engineering, Jilin Jianzhu University, Changchun 130118, China
Abstract: After applying raster processing to the point cloud data collected by Z+F IMAGER 5010C scanner in the experimental area, combined with texture and shape information, the point cloud data are classified using the spectral clustering algorithm, and subsequently the accuracy of classification is evaluated by the Kappa coefficient in confusion matrix. Compared with the classification results of traditional K-means algorithm and Gaussian mixture model, the spectral clustering algorithm has more distinct classification effect and higher classification accuracy. Moreover, adding texture and shape information leads to higher accuracy than that only uses reflection intensity information. The overall accuracy of the classification is 81.36%, and the Kappa coefficient is 0.713 8.
Keywords: 3D laser scanning   point cloud data   spectral clustering algorithm   Kappa coefficient  
收稿日期 2019-12-21 修回日期 2020-03-27 网络版发布日期  
DOI: 10.3969/j.issn.1004-5589.2020.02.024
基金项目:

国家自然科学基金项目（41472243，4182010400）、国土资源部地面沉降检测与防治重点实验室开放基金项目（KLLSMP201901）与国土资源部城市土地资源监测与仿真重点实验室开放基金项目（KF-2018-03-20）联合资助。

通讯作者: 王凤艳(1970-),女,教授,博士,从事工程测量和相机标定方面的研究。E-mail:wangfy@jlu.edu.cn
作者简介:
作者Email: wangfy@jlu.edu.cn
参考文献：
[1] 戴升山, 李田凤. 地面三维激光扫描技术的发展与应用前景[J]. 现代测绘, 2009, 32(4):11-12, 15. DAI Sheng-shan, LI Tian-feng. The development and application prospects of ground three-dimensional laser scan technology[J]. Modern Surveying and Mapping, 2009, 32(4):11-12, 15.
[2] 马立广. 地面三维激光扫描仪的分类与应用[J]. 地理空间信息, 2005, 3(3):60-62. MA Li-guang. Classification and application of terrestrial laser scanners[J]. Geospatial Information, 2005, 3(3):60-62.
[3] 李真, 汪沛, 张青. 树干与地面点云分类K-means方法的改进[J]. 东北林业大学学报, 2019, 47(1):41-46. LI Zhen, WANG Pei, ZHANG Qing. An improved method for tree trunks and ground point clouds by K-means cluster analysis[J]. Journal of Northeast Forestry University, 2019, 47(1):41-46.
[4] 胡健. 遥感影像的云雪检测算法与地表反射率库构建算法研究:硕士学位论文[D]. 开封:河南大学, 2017. HU Jian. Study on algorithm of cloud-snow detection and algorithm of surface reflectivity library for remote sensing image:master's degree thesis[D]. Kaifeng:Henan University, 2017.
[5] Zhang Z X, Zhang L Q, Tong X H, et al. A multilevel point-cluster-based discriminative feature for ALS point cloud classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(6):3309-3321.
[6] Lai K, Fox D. Object recognition in 3D point clouds using web data and domain adaptation[J]. The International Journal of Robotics Research, 2010, 29(8):1019-1037.
[7] 王书民, 李文宁, 张爱武. 采用模糊C均值方法进行激光点云分类[J]. 测绘通报, 2016(10):21-24, 30. WANG Shu-min, LI Wen-ning, ZHANG Ai-wu. The classification of laser point clouds using fuzzy C-means method[J]. Bulletin of Surveying and Mapping, 2016(10):21-24, 30.
[8] 袁夏, 赵春霞, 张浩峰, 等. 基于点云数据的自然地形分类算法[J]. 南京理工大学学报(自然科学版), 2010, 34(2):222-226, 237. YUAN Xia, ZHAO Chun-xia, ZHANG Hao-feng, et al. Nature terrain classification using point cloud data[J]. Journal of Nanjing University of Science and Technology (Natural Science), 2010, 34(2):222-226, 237.
[9] 倪明, 文加林, 丁仁军, 等. 三维激光扫描中点云分类的研究与实现:以昆明市历史文化街区光华街为例[J]. 地矿测绘, 2014, 30(2):32-35. NI Ming, WEN Jia-lin, DING Ren-jun, et al. Research and implementation of 3D laser scanning point cloud classification:with historic area in Guanghua street of Kunming as an example[J]. Surveying and Mapping of Geology and Mineral Resources, 2014, 30(2):32-35.
[10] 黄吉. 一种K-means聚类改进算法研究及应用:硕士学位论文[D]. 武汉:湖北工业大学, 2018. HUANG Ji. Research and application on K-means clustering improved algorithm:master's degree thesis[D]. Wuhan:Hubei University of Technology, 2018.
[11] 高琰, 谷士文, 唐琎, 等. 机器学习中谱聚类方法的研究[J]. 计算机科学, 2007, 34(2):201-203. GAO Yan, GU Shi-wen, TANG Jin, et al. Research on spectral clustering in machine learning[J]. Computer Science, 2017, 34(2):201-203.
[12] 万月. 谱聚类算法的研究及其应用:硕士学位论文[D]. 无锡:江南大学, 2017. WAN Yue. Research and application of spectral clustering algorithm:master's degree thesis[D]. Wuxi:Jiangnan University, 2017.
[13] 张彩霞, 胡红萍, 白艳萍. 基于稀疏子空间聚类的人脸识别方法[J]. 火力与指挥控制, 2017, 42(4):29-32. ZHANG Cai-xia, HU Hong-ping, BAI Yan-ping. Face recognition method based on sparse subspace clustering[J]. Fire Control & Command Control, 2017, 42(4):29-32.
[14] Janani R, Vijayarani S. Text document clustering using spectral clustering algorithm with particle swarm optimization[J]. Expert Systems with Applications, 2019, 134:192-200.
[15] Dey T K, Peng P, Rossi A, et al. Spectral concentration and greedy K-clustering[J]. Computational Geometry:Theory and Applications, 2019, 76:19-32.
[16] Haralick R M, Shanmugam K, Dinstein I. Textural features for image classification[J]. IEEE Transaction on Systems, Man, and Cybernetics, 1973, 3(6):610-621.
[17] Luque A, Carrasco A, Martín A, et al. The impact of class imbalance in classification performance metrics based on the binary confusion matrix[J]. Pattern Recognition, 2019, 91:216-231.
本刊中的类似文章
1．国策, 杨国东, 王民水, 詹国旗, 王凤艳, 王伟.三维激光扫描装置设计与数据处理[J]. 世界地质, 2018,37(4): 1231-1238
2．卢立吉, 王凤艳, 王明常, 李启源.基于误差理论的产状测量精度评定[J]. 世界地质, 2016,35(2): 567-574
Copyright by 世界地质