留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于阈值的激光雷达K均值聚类算法

夏显召 朱世贤 周意遥 叶茂 赵毅强

夏显召, 朱世贤, 周意遥, 等 . 基于阈值的激光雷达K均值聚类算法[J]. 北京航空航天大学学报, 2020, 46(1): 115-121. doi: 10.13700/j.bh.1001-5965.2019.0113
引用本文: 夏显召, 朱世贤, 周意遥, 等 . 基于阈值的激光雷达K均值聚类算法[J]. 北京航空航天大学学报, 2020, 46(1): 115-121. doi: 10.13700/j.bh.1001-5965.2019.0113
XIA Xianzhao, ZHU Shixian, ZHOU Yiyao, et al. LiDAR K-means clustering algorithm based on threshold[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(1): 115-121. doi: 10.13700/j.bh.1001-5965.2019.0113(in Chinese)
Citation: XIA Xianzhao, ZHU Shixian, ZHOU Yiyao, et al. LiDAR K-means clustering algorithm based on threshold[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(1): 115-121. doi: 10.13700/j.bh.1001-5965.2019.0113(in Chinese)

基于阈值的激光雷达K均值聚类算法

doi: 10.13700/j.bh.1001-5965.2019.0113
基金项目: 

天津市科技计划 18ZXZNGX00230

详细信息
    作者简介:

    夏显召  男, 博士研究生。主要研究方向:多传感器信号处理和融合算法

    朱世贤  男, 硕士研究生。主要研究方向:激光雷达数据采集和处理

    周意遥  男, 硕士研究生。主要研究方向:激光雷达点云数据处理

    叶茂  男, 博士, 讲师。主要研究方向:混合信号集成电路和传感器接口电路

    赵毅强  男, 博士, 教授。主要研究方向:混合信号集成电路、安全芯片、光电成像系统和传感器系统

    通讯作者:

    赵毅强,E-mail:yq_zhao@tju.edu.cn

  • 中图分类号: TN958.98;TN911.74

LiDAR K-means clustering algorithm based on threshold

Funds: 

Science and Technology Project of Tianjin 18ZXZNGX00230

More Information
  • 摘要:

    针对同一距离不同目标的激光雷达全波形回波数据聚类准确率低的问题,在分析K均值聚类算法原理的基础上,提出了一种基于阈值的K均值聚类算法。首先,利用强度信息对距离信息进行标定,使用强度信息作为特征进行聚类以区分同距离的不同目标。然后,利用阈值限定聚类中心间的最小距离,提高聚类准确率。最后,搭建了扫描验证平台进行平移和旋转成像,对算法有效性进行验证。通过不同颜色目标和模拟道路回波数据聚类实验表明,在不同阈值的情况下,提出的基于阈值的K均值聚类算法的聚类准确率均在90%以上,相比于无阈值的K均值聚类算法准确率提升10%以上,能够有效进行目标聚类和模拟道路提取。

     

  • 图 1  基于阈值的K均值聚类算法流程图

    Figure 1.  Flowchart of threshold-based K-means clustering algorithm

    图 2  聚类仿真结果

    Figure 2.  Clustering simulation results

    图 3  聚类准确率与阈值的关系

    Figure 3.  Relationship between clustering accuracy and threshold

    图 4  扫描平台

    Figure 4.  Scanning platform

    图 5  扫描平台的扫描方式

    Figure 5.  Scanning method of scanning platform

    图 6  目标实物图

    Figure 6.  Photo of actual target

    图 7  无阈值的K均值聚类算法结果

    Figure 7.  Threshold-free K-means clustering algorithm results

    图 8  基于阈值的K均值聚类算法结果

    Figure 8.  Threshold-based K-means clustering algorithm result

    图 9  道路路线模拟

    Figure 9.  Road route simulation

    图 10  模拟道路线实验结果

    Figure 10.  Simulated road line experiment results

  • [1] XU W, CHEN Q, GU G H.Research on laser ranging system based on time delay estimation[C]//Symposium on Photonics & Optoelectronics.Piscataway, NJ: IEEE Press, 2011: 1-3.
    [2] 王金虎, 李传荣, 周梅.机载全波形激光雷达数据处理及其应用[J].国外电子测量技术, 2012, 31(6):71-75. doi: 10.3969/j.issn.1002-8978.2012.06.020

    WANG J H, LI C R, ZHOU M.Data processing and application of airborne full waveform LiDAR[J].Journal of Foreign Electronic Measurement Technology, 2012, 31(6):71-75(in Chinese). doi: 10.3969/j.issn.1002-8978.2012.06.020
    [3] WARDG J.Measuring and modeling anisotropic reflection[J].ACM SIGGRAPH Computer Graphics, 1992, 26(2):265-272. doi: 10.1145/142920.134078
    [4] MILIARESIS G, KOKKAS N.Segmentation and object-based classification for the extraction of the building class from LIDAR DEMs[J].Computers & Geosciences, 2007, 33:1076-1087. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=4fc6e984822cfbbfd2b726bb104404e8
    [5] SANDEEP G, HOLGER W, BARBARA K.Comparative analysis of clustering-based approaches for 3-D single tree detection using airborne fullwave LiDAR data[J].Remote Sensing, 2010, 2(4):968-989. doi: 10.3390/rs2040968
    [6] SAMPATH A, SHAN J.Segmentation and reconstruction of polyhedral building roofs from aerial LiDAR point clouds[J].IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(3):1554-1567. doi: 10.1109/TGRS.2009.2030180
    [7] 龚亮, 张永生, 李正国, 等.基于强度信息聚类的机载LiDAR点云道路提取[J].测绘通报, 2011(9):15-17. http://d.old.wanfangdata.com.cn/Periodical/chtb201109005

    GONG L, ZHANG Y S, LI Z G, et al.Airborne LiDAR point cloud road extraction based on intensity information clustering[J].Journal of Bulletin of Surveying and Mapping, 2011(9):15-17(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/chtb201109005
    [8] KONG D, XU L J, LI X L, et al.K-plane-based classification of airborne LiDAR data for accurate building roof measurement[J].IEEE Transactions on Instrumentation & Measurement, 2014, 63(5):1200-1214. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=2a85ff746b4798c80780591ff6638279
    [9] DÍAZ-VILARIÑO L, GONZÁLEZ-JORGE H, BUENO M, et al.Automatic classification of urban pavements using mobile LiDAR data and roughness descriptors[J].Construction and Building Materials, 2015, 102(1):208-215. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=105f9c8eddd30a230fe7be4bc24875f1
    [10] KASHANI A G, GRAETTINGER A J.Cluster-based roof covering damage detection in ground-based LiDAR data[J].Automation in Construction, 2015, 58:19-27. doi: 10.1016/j.autcon.2015.07.007
    [11] CHEN J, ZHU H, LI X.Automatic extraction of discontinuity orientation from rock mass surface 3D point cloud[J].Computers & Geosciences, 2016, 95:18-31. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=02f9a0ee614586611533d0877cfa65e9
    [12] CHUYEN N, MICHAEL S, PHILIPPE T, et al. Unsupervised clustering method for complexity reduction of terrestrial LiDAR data in marshes[J].Remote Sensing, 2018, 10(1):133-154. doi: 10.3390/rs10010133
    [13] RENATO C D S, MAURICIO G, VILMA M T.Classification of LiDAR data over building roofs using k means and principal component analysis[J].Boletim de Ciênccas Geodésicas, 2018, 24(1):69-84. doi: 10.1590/s1982-21702018000100006
    [14] NIMA E, CRAIG G, CARLOS F D J.Classification of airborne multispectral LiDAR point clouds for land cover mapping[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(6):2068-2078. doi: 10.1109/JSTARS.2018.2835483
    [15] LI X, LIANG Y, XU L.Bidirectional reflectance distribution function based surface modeling of non-Lambertian using intensity data of light detection and ranging[J].Journal of the Optical Society of America A, 2014, 31(9):2055. doi: 10.1364/JOSAA.31.002055
  • 加载中
图(10)
计量
  • 文章访问数:  448
  • HTML全文浏览量:  2
  • PDF下载量:  172
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-03-19
  • 录用日期:  2019-07-05
  • 刊出日期:  2020-01-20

目录

    /

    返回文章
    返回
    常见问答