首页 > 论文 > 激光与光电子学进展 > 56卷 > 12期(pp:122801--1)

基于激光雷达点云数据的树种分类

Classification of Tree Species Based on LiDAR Point Cloud Data

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

摘要

以杭州钱江新城森林公园和新疆维吾尔自治区阿克苏市红旗坡农场的水杉、柳树、女贞、竹子和苹果树为研究对象,基于机载LiDAR获取高分辨率点云数据,结合支持向量机分类器,提出了多种树木特征,如结构特征参数、纹理特征参数和冠形特征参数等,以实现树种分类。实验结果表明,5种树木分类的整体准确率达85%,Kappa系数为0.81。所提分类方法不仅从LiDAR数据中获得了更有前景的单株树特征,还展示了一个可用于提高树种分类性能的有效框架。

Abstract

This study involved the Metasequoia glyptostroboides, Salix babylonica, Ligustrum lucidum, bamboo, and Malus pumila Mill. from the Qianjiang new town forest park of the Hangzhou city and the Hongqipo farm of the Aksu city in the Xinjiang Uygur Autonomous Region. The structural, textural, and crown features were proposed based on high-resolution point cloud data acquired by the airborne LiDAR and a support vector machine classifier. The experimental results demonstrate that the overall accuracy of the classification is 85%, with a Kappa coefficient of 0.81. The proposed method derives promising features for a tree based on the LiDAR data and demonstrates an effective framework for improving the classification performance of the tree species.

中国激光微信矩阵
补充资料

中图分类号:S771

DOI:10.3788/LOP56.122801

所属栏目:遥感与传感器

基金项目:国家重点研发计划、国家自然科学基金、中国博士后面上基金项目、江苏高校优势学科建设工程项目;

收稿日期:2018-11-23

修改稿日期:2019-01-09

网络出版日期:2019-06-13

作者单位    点击查看

陈向宇:南京林业大学信息科学技术学院, 江苏 南京 210037
云挺:南京林业大学信息科学技术学院, 江苏 南京 210037
薛联凤:南京林业大学信息科学技术学院, 江苏 南京 210037
刘应安:南京林业大学图书馆, 江苏 南京 210037

联系人作者:陈向宇(1016733396@qq.com); 刘应安( lyastat@163.com);

备注:国家重点研发计划、国家自然科学基金、中国博士后面上基金项目、江苏高校优势学科建设工程项目;

【1】Lu X K. Tree species classification and 3D visualization based on airborne LiDAR and hyperspectral data. Chengdu: University of Electric Science and Technology of China. (2018).
鲁续坤. 基于机载LiDAR和高光谱数据的树种分类及三维显示. 成都: 电子科技大学. (2018).

【2】Zhao F. Forest parameter extraction using LiDAR data and digital camera image. Beijing: Chinese Academy of Forestry. (2007).
赵峰. 机载激光雷达数据和数码相机影像林木参数提取研究. 北京: 中国林业科学研究院. (2007).

【3】Anitha K, Joseph S, Chandran R J et al. Tree species diversity and community composition in a human-dominated tropical forest of Western Ghats biodiversity hotspot, India. Ecological Complexity. 7(2), 217-224(2010).

【4】Heinzel J and Koch B. Investigating multiple data sources for tree species classification in temperate forest and use for single tree delineation. International Journal of Applied Earth Observation and Geoinformation. 18, 101-110(2012).

【5】Wang C Y, Wang A L, Wang J Y et al. Coastal zone land use information extraction based on objectoriented classification method. Journal of Natural Resources. 29(9), 1589-1597(2014).
王彩艳, 王瑷玲, 王介勇 等. 基于面向对象的海岸带土地利用信息提取研究. 自然资源学报. 29(9), 1589-1597(2014).

【6】Holmgren J and Persson . Identifying species of individual trees using airborne laser scanner. Remote Sensing of Environment. 90(4), 415-423(2004).

【7】Hollaus M, Wagner W, Eberh fer C et al. Accuracy of large-scale canopy heights derived from LiDAR data under operational constraints in a complex alpine environment. ISPRS Journal of Photogrammetry and Remote Sensing. 60(5), 323-338(2006).

【8】Liu Q W, Li Z Y, Chen E X et al. Extracting height and crown of individual tree using airborne LiDAR data. Journal of Beijing Forestry University. 30(6), 83-89(2008).
刘清旺, 李增元, 陈尔学 等. 利用机载激光雷达数据提取单株木树高和树冠. 北京林业大学学报. 30(6), 83-89(2008).

【9】Zhao D. Individual tree parameters extraction based on lidar and hyper-spectrum data. Beijing: Chinese Academy of Forestry. (2012).
赵旦. 基于激光雷达和高光谱遥感的森林单木关键参数提取. 北京: 中国林业科学研究院. (2012).

【10】Li J L, Hu B X and Forest Meteorology. 171/172, 104-114(2013).

【11】Wei T. Tree-level structure characterization based on static terrestrial laser scanning point clouds. Tangshan: North China University of Science and Technology. (2015).
魏田. 基于静态地基激光扫描点云的单树结构表征. 唐山: 华北理工大学. (2015).

【12】Cao L, Coops N C, Innes J L et al. Tree species classification in subtropical forests using small-footprint full-waveform LiDAR data. International Journal of Applied Earth Observation and Geoinformation. 49, 39-51(2016).

【13】Wang J, Zhang L Y, Lü C D et al. Tree species identification methods based on point cloud data using ground-based LiDAR. Transactions of the Chinese Society of Agricultural Machinery. 49(11), 180-188(2018).
王佳, 张隆裕, 吕春东 等. 基于地面激光雷达点云数据的树种识别方法. 农业机械学报. 49(11), 180-188(2018).

【14】Kantola T, Vastaranta M, Yu X W et al. Classification of defoliated trees using tree-level airborne laser scanning data combined with aerial images. Remote Sensing. 2(12), 2665-2679(2010).

【15】Puttonen E, Suomalainen J, Hakala T et al. Tree species classification from fused active hyperspectral reflectance and LiDAR measurements. Forest Ecology and Management. 260(10), 1843-1852(2010).

【16】Lin Y and Hyypp J. A comprehensive but efficient framework of proposing and validating feature parameters from airborne LiDAR data for tree species classification. International Journal of Applied Earth Observation and Geoinformation. 46, 45-55(2016).

【17】Haralick R M and Shanmugam K. SMC-. Dinstein I. Textural features for image classification. IEEE Transactions on Systems, Man, Cybernetics. 3(6), 610-621(1973).

【18】Wei X H, Wang Y G, Zheng J et al. Tree crown volume calculation based on 3-D laser scanning point clouds data. Transactions of the Chinese Society for Agricultural Machinery. 44(7), 235-240(2013).
韦雪花, 王永国, 郑君 等. 基于三维激光扫描点云的树冠体积计算方法. 农业机械学报. 44(7), 235-240(2013).

【19】Xu W H, Feng Z K, Su Z F et al. An automatic extraction algorithm for individual tree crown projection area and volume based on 3D point cloud data. Spectroscopy and Spectral Analysis. 34(2), 465-471(2014).
徐伟恒, 冯仲科, 苏志芳 等. 一种基于三维激光点云数据的单木树冠投影面积和树冠体积自动提取算法. 光谱学与光谱分析. 34(2), 465-471(2014).

【20】Zhang D, Yan R, Yun T et al. The 3D reconstruction of tree branches from point cloud based on terrestrial laser scanner. Journal of Forestry Engineering. 1(5), 107-114(2016).
张冬, 严锐, 云挺 等. 基于地面激光雷达的单木枝干建模方法. 林业工程学报. 1(5), 107-114(2016).

引用该论文

Xiangyu Chen,Ting Yun,Lianfeng Xue,Ying'an Liu. Classification of Tree Species Based on LiDAR Point Cloud Data[J]. Laser & Optoelectronics Progress, 2019, 56(12): 122801

陈向宇,云挺,薛联凤,刘应安. 基于激光雷达点云数据的树种分类[J]. 激光与光电子学进展, 2019, 56(12): 122801

被引情况

【1】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. 激光与光电子学进展, 2019, 56(16): 161002--1

【2】钱其姝,胡以华,赵楠翔,李敏乐,邵福才. 基于激光点云全局特征匹配处理的目标跟踪算法. 激光与光电子学进展, 2020, 57(6): 61012--1

【3】方晓玉,李晓斌,郭震. 一种改进的混合灰狼优化支持向量机预测算法及应用. 激光与光电子学进展, 2020, 57(12): 122801--1

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