南京林业大学学报(自然科学版) ›› 2024, Vol. 48 ›› Issue (4): 123-131.doi: 10.12302/j.issn.1000-2006.202211006

所属专题: 专题报道Ⅲ:智慧林业之森林可视化研究

• 专题报道Ⅲ:智慧林业之森林可视化研究(执行主编 李凤日、张怀清、曹林) • 上一篇    下一篇

改进分类回归树模型的青冈枝叶点云分类研究

潘政尚1(), 马开森1, 龙依1, 赖珍贵2, 孙华1,*()   

  1. 1.中南林业科技大学林业遥感信息工程研究中心,林业遥感大数据与生态安全湖南省重点实验室,南方森林资源经营与监测国家林业和草原局重点实验室,湖南长沙 410004
    2.中南林业科技大学芦头实验林场,湖南 岳阳 414000
  • 收稿日期:2022-11-04 修回日期:2022-12-28 出版日期:2024-07-30 发布日期:2024-08-05
  • 通讯作者: *孙华(sunhua@csuft.edu.cn),教授。
  • 作者简介:

    潘政尚(20201100030@csuft.edu.cn)。

  • 基金资助:
    国家自然科学基金面上项目(31971578);湖南省自然科学基金面上项目(2022JJ30078);湖南省科技创新计划(2023RC1065)

An improved CART model for leaf and wood classification from LiDAR point clouds of Quercus glauca individual trees

PAN Zhengshang1(), MA Kaisen1, LONG Yi1, LAI Zhengui2, SUN Hua1,*()   

  1. 1. Research Center of Forestry Remote Sensing & Information Engineering, Central South University of Forestry and Technology, Key Laboratory of Forestry Remote Sensing Based Big Data & Ecological Security for Hunan Province, Key Laboratory of National Forestry and Grassland Administration on Forest Resources Management and Monitoring in Southern China, Changsha 410004, China
    2. Lutou Experimental Forest Farm, Central South University of Forestry and Technology, Yueyang 414000, China
  • Received:2022-11-04 Revised:2022-12-28 Online:2024-07-30 Published:2024-08-05

摘要:

【目的】传统的树木枝叶点云分类模型结构与特征过于复杂,存在稳定性差、精度低、模型过拟合及计算成本高等问题。研究以阔叶树青冈(Quercus glauca)地面激光点云数据为基础,提出一种改进的分类回归树(classification and regression tree, CART)枝叶点云分类模型。【方法】首先根据点的邻域特征构造特征描述子,确定邻域搜索参数的最佳取值。通过逐步引入变量和调整决策树模型结构实现对分类回归树模型的改进。将改进后模型的分类结果与Logistics回归和K近邻模型进行对比。【结果】特征描述子作为变量引入后,模型测试数据分类准确率有所提升,比Logistics回归和K近邻模型分别高出13.1%和13.6%;改进后的分类回归树模型准确率有较大提升,稳定性好且模型大小显著降低,模型大小较改进前减少了99.9%,数据训练时间仅为调整前的51.3%;改进后的方法在树干和树叶上的综合评价指标均在0.9左右,差距小于0.001,无过拟合现象。【结论】改进的CART模型具有较高的精度,在小样本上也能取得较好的分类效果,稳定性好。研究结果可为地面激光雷达枝叶点云精准快速分类提供参考。

关键词: 地面激光雷达, 点云分类, 点云特征, 分类回归树

Abstract:

【Objective】Due to the complex structure and features, traditional classification models for tree branches and leaf point clouds typically face several problems, including poor stability, low accuracy, model overfitting, and high computational costs. In this study, we propose an improved CART (classification and regression tree) model for leaf and branch classification based on Quercus glauca individual tree point cloud data from terrestrial laser LiDAR.【Method】First, the feature descriptor was constructed according to the neighborhood points, and the optimal value of the neighborhood search parameter was then determined. The CART model was improved by gradually introducing variables and adjusting the structure of the decision tree. The classification results of the improved CART model were compared with those of the Logistics regression and K-nearest neighbor (KNN) models.【Result】The accuracy of the improved CART model using the test data increased after introducing the feature descriptors as variables, exceeding that of the Logistics regression and KNN model by 13.1% and 13.6%, respectively. Moreover, the improved CART model exhibited higher accuracy, better stability, and marked reduced model size following the improvement. In particular, the model size was reduced by 99.9% compared with before the improvement, while the data training time was only 51.3% of that before the adjustment. The comprehensive evaluation index of the improved CART model was approximately 0.9 on both trunk and leaf data, with the difference between accuracy on train data and test data lower than 0.001, indicating no overfitting.【Conclusion】The improved CART model has a high accuracy and stability, and achieves good classification results on small samples. This study provides a methodological reference for the accurate and rapid classification of trunk and leaf point clouds from terrestrial laser LiDAR.

Key words: terrestrial laser LiDAR, point cloud classification, point cloud features, classification and regression tree

中图分类号: