首页 > 论文 > 中国激光 > 46卷 > 5期(pp:510002--1)

基于树木激光点云的有效特征抽取与识别方法

Effective Feature Extraction and Identification Method Based on Tree Laser Point Cloud

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

摘要

采用地面激光扫描获取树木的光探测和测距数据,并将其作为遥感数据源,选取水杉、棕榈、无患子、竹子和橡胶树为研究对象,提出了三类有效特征:树木相对聚类特征、点云分布特征和树木表观特征,列举了68个特征参数。采用支持向量机在交叉验证中对训练数据集进行检验计算,确定最优的特征参数组,最终在测试数据集中进行树种分类。研究结果表明:基于树木相对聚类特征的最优特征参数组进行树种分类的平均分类精度较低(45%);基于点云分布特征的最优特征参数组进行树种分类的平均分类精度有所增加(58.8%);基于树木表观特征的最优特征参数组进行树种分类的平均分类精度较高(63.8%);基于三类特征的13个最优特征参数进行树种分类的平均分类精度最高(87.5%)。此外,由于水杉与其他树种形态差异较为明显,在分类中表现突出,错判率最低(6.5%)。所提方法具有较高的可行性,为获得更准确的森林树种分布提供了强有力的工具。

Abstract

Herein, light detection and ranging data were collected as remoting data sources by terrestrial laser scanning (TLS). Metasequoia, palm, sapindus, bamboo, and rubber trees were selected as research objects. Three effective features are proposed, which are relative clustering features of trees, features of point cloud distribution of trees, and apparent features of trees. 68 feature parameters are listed. A support vector machine (SVM) classifier was then used to verify and calculate the training dataset and to determine the optimal feature parameters in cross-validation. Finally, the tree species is classified in the test dataset. The research results show that the average classification accuracy of tree classification based on the optimal parameters of relative clustering features of trees is low (45%), that based on the optimal feature parameters of point cloud distribution slightly increases (58.8%), that based on the optimal parameters of tree appearance features is relatively high (63.8%), and that based on the 13 optimal parameters of three types of features is the highest (87.5%). In addition, due to the difference between metasequoia and other tree species is obvious, the metasequoia is outstanding in classification and its misjudgement rate is the lowest (6.5%). The proposed method has high feasibility and provides a powerful tool for obtaining a more accurate distribution of forest species.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:S771

DOI:10.3788/cjl201946.0510002

所属栏目:遥感与传感器

基金项目:国家重点研发计划(2017YFD0600900)、国家自然科学基金项目(31770591)、中国博士后面上基金(2016M601823)

收稿日期:2018-12-04

修改稿日期:2019-01-20

网络出版日期:2019-02-18

作者单位    点击查看

卢晓艺: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南京林业大学南方现代林业协同创新中心, 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
徐强法:南京林业大学信息科学技术学院, 江苏 南京 210037
曹林:南京林业大学南方现代林业协同创新中心, 江苏 南京 210037

联系人作者:联系作者(xuelianfeng@njfu.edu.cn)

【1】Shi Y F, Skidmore A K, Wang T J, et al. Tree species classification using plant functional traits from LiDAR and hyperspectral data[J]. International Journal of Applied Earth Observation and Geoinformation, 2018, 73: 207-219.

【2】Skidmore A K, Pettorelli N, Coops N C, et al. Environmental science: agree on biodiversity metrics to track from space[J]. Nature, 2015, 523(7561): 403-405.

【3】Bruggisser M, Roncat A, Schaepman M E, et al. Retrieval of higher order statistical moments from full-waveform LiDAR data for tree species classification[J]. Remote Sensing of Environment, 2017, 196: 28-41.

【4】Harrison D, Rivard B, Sánchez-Azofeifa A. Classification of tree species based on longwave hyperspectral data from leaves, a case study for a tropical dry forest[J]. International Journal of Applied Earth Observation and Geoinformation, 2018, 66: 93-105.

【5】Fassnacht F E, Latifi H, Stereńczak K, et al. Review of studies on tree species classification from remotely sensed data[J]. Remote Sensing of Environment, 2016, 186: 64-87.

【6】Moore M M, Bauer M E. Classification of forest vegetation in north-central Minnesota using Landsat Multispectral Scanner and Thematic Mapper data[J]. Forest Science, 1990, 36(2): 330-342.

【7】Walsh S J. Coniferous tree species mapping using LANDSAT data[J]. Remote Sensing of Environment, 1980, 9(1): 11-26.

【8】Zhang C Y, Qiu F. Mapping individual tree species in an urban forest using airborne lidar data and hyperspectral imagery[J]. Photogrammetric Engineering & Remote Sensing, 2012, 78(10): 1079-1087.

【9】Richter R, Reu B, Wirth C, et al. The use of airborne hyperspectral data for tree species classification in a species-rich Central European forest area[J]. International Journal of Applied Earth Observation and Geoinformation, 2016, 52: 464-474.

【10】Pant P, Heikkinen V, Hovi A, et al. Evaluation of simulated bands in airborne optical sensors for tree species identification[J]. Remote Sensing of Environment, 2013, 138: 27-37.

【11】Liu H J, Wu C S. Crown-level tree species classification from AISA hyperspectral imagery using an innovative pixel-weighting approach[J]. International Journal of Applied Earth Observation and Geoinformation, 2018, 68: 298-307.

【12】Cho M A, Debba P, Mathieu R, et al. Improving discrimination of savanna tree species through a multiple-endmember spectral angle mapper approach: canopy-level analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010: 48(11): 4133-4142.

【13】Pinacho-Pinacho C D, García-Varela M, Sereno-Uribe A L, et al. A hyper-diverse genus of Acanthocephalans revealed by tree-based and non-tree-based species delimitation methods: ten cryptic species of Neoechinorhynchus in Middle American freshwater fishes[J]. Molecular Phylogenetics and Evolution, 2018, 127: 30-45.

【14】kerblom M, Raumonen P, Mkip R, et al. Automatic tree species recognition with quantitative structure models[J]. Remote Sensing of Environment, 2017, 191: 1-12.

【15】do Amaral C H, de Almeida T I R, de Souza Filho C R, et al. Characterization of indicator tree species in neotropical environments and implications for geological mapping[J]. Remote Sensing of Environment, 2018, 216: 385-400.

【16】Strnad D, Kohek , Kolmani S. Fuzzy modelling of growth potential in forest development simulation[J]. Ecological Informatics, 2018, 48: 80-88.

【17】Piiroinen R, Fassnacht F E, Heiskanen J, et al. Invasive tree species detection in the Eastern Arc Mountains biodiversity hotspot using one class classification[J]. Remote Sensing of Environment, 2018, 218: 119-131.

【18】Heinzel J, Koch B. Corrigendum to “investigating multiple data sources for tree species classification in temperate forest and use for single tree delineation”[J]. International Journal of Applied Earth Observation and Geoinformation, 2013, 21: 101-110.

【19】Huang Z W, Liu F, Hu G W. Improved method for LiDAR point cloud data filtering based on hierarchical pseudo-grid[J]. Acta Optica Sinica, 2017, 37(8): 0828004.
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[J]. 光学学报, 2017, 37(8): 0828004.

【20】Teng W X, Wen X R, Wang N, et al. Individual tree crown extraction in high resolution remote sensing image based on iterative H-minima improved watershed algorithm[J]. Laser & Optoelectronics Progress, 2018, 55(12): 122802.
滕文秀, 温小荣, 王妮, 等. 基于迭代H-minima改进分水岭算法的高分辨率遥感影像单木树冠提取[J]. 激光与光电子学进展, 2018, 55(12): 122802.

【21】Yun T, An F, Li W Z, et al. A novel approach for retrieving tree leaf area from ground-based LiDAR[J]. Remote Sensing, 2016, 8(11): 942.

引用该论文

Lu Xiaoyi,Yun Ting,Xue Lianfeng,Xu Qiangfa,Cao Lin. Effective Feature Extraction and Identification Method Based on Tree Laser Point Cloud[J]. Chinese Journal of Lasers, 2019, 46(5): 0510002

卢晓艺,云挺,薛联凤,徐强法,曹林. 基于树木激光点云的有效特征抽取与识别方法[J]. 中国激光, 2019, 46(5): 0510002

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