针对现有基于地面端的树木点云分割方法因局部与全局特征信息融合不足导致分割精度下降的问题，提出了一种基于空间邻近关系的森林样地树木分割方法。首先，通过构建八叉树索引建立空间关系并分离地面点，在此基础上，建立多阶段的随机森林模型实现树木点云渐进式分割，即利用树干截面的二维形态特征及空间特性准确分割树干点云；其次，基于树干点云的分割结果，利用优化的形状函数集合（ensemble of shape functions,ESF）特征描述算子获取树干与对应树冠点云间的空间连通特征，并结合树冠点云的维度特性对树冠点云进行分割；最后，对单棵树木进行结构参数的提取，并与实地测量值进行对比以完成精度评价。本文利用两组移动激光扫描点云进行实验，结果表明两组数据中树木分割的召回率分别为90.57%和90.05%，精确率分别为93.20%和95.47%。
To address the problem of reduced segmentation accuracy in current ground-based tree point cloud segmentation methods caused by insufficient integration of local and global feature information, this paper proposes a tree segmentation method for forest sample plots based on spatial proximity relationship. This method first establishes the spatial relationship and separates the ground points by constructing an octree index. On this basis, a multi-stage random forest model is developed to achieve progressive segmentation of the tree point cloud. Specifically, the two-dimensional morphological features and spatial properties of tree trunk cross-section are used to accurately segment tree trunk point cloud. Subsequently, based on the segmentation results, the optimized ensemble of shape functions (ESF) feature description operator is used to obtain the spatial connectivity features between the tree trunk and the corresponding tree crown point cloud, enabling crown segmentation by incorporating dimensional properties of the tree crown point cloud. Finally, the structural parameters are extracted for single trees and validated against field measurements. Experiments using two sets of mobile laser scanning point cloud data show that the proposed method achieves tree segmentation recall rates of 90.57% and 90.05%, with accuracies of 93.20% and 95.47%, respectively.
[1] Liu J, Skidmore A K, Wang T J, et al. Variation of leaf angle distribution quantified by terrestrial LiDAR in natural European beech forest [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 148: 208-220.
[2] 徐来仙, 何友均, 艾训儒, 等. 基于森林生态系统服务权衡与协同的森林可持续管理[J]. 生态学报, 2024, 44(4): 1347-1359. Xu L X, He Y J, Ai X R, et al. Sustainable management of forests based on trade-offs and synergies of forest ecosystem services [J]. Acta Ecologica Sinica, 2024, 44(4): 1347-1359. (in Chinese)
[3] Brolly G, Király G, Lehtomäki M, et al. Voxel-based automatic tree detection and parameter retrieval from terrestrial laser scans for plot-wise forest inventory [J]. Remote Sensing, 2021, 13(4): 542.
[4] 孔丹, 庞勇, 梁晓军, 等. 基于分层叠加的机载LiDAR点云单木分割[J]. 林业科学, 2024, 60(3): 87-99. Kong D, Pang Y, Liang X J, et al. Individual tree segmentation from ALS point clouds based on layers stacking algorithm [J]. Scientia Silvae Sinicae, 2024, 60(3): 87-99. (in Chinese)
[5] 张怡卓, 吕阿康, 蒋大鹏, 等. 应用高斯聚类的单木分割及树高和冠幅的提取[J]. 东北林业大学学报, 2021, 49(2): 54-59. Zhang Y Z, Lv A K, Jiang D P, et al. Single tree segmentation and extraction of tree height and crown width using Gaussian clustering [J]. Journal of Northeast Forestry University, 2021, 49(2): 54-59. (in Chinese)
[6] 甄贞, 李响, 修思玉, 等. 基于标记控制区域生长法的单木树冠提取[J]. 东北林业大学学报, 2016, 44(10): 22-29. Zhen Z, Li X, Xiu S Y, et al. Individual tree crown delineation using maker-controlled region growing method [J]. Journal of Northeast Forestry University, 2016, 44(10): 22-29. (in Chinese)
[7] Zhang Y, Liu H, Liu X, et al. Towards intricate stand structure: a novel individual tree segmentation method for ALS point cloud based on extreme offset deep learning [J]. Applied Sciences, 2023, 13(11): 6853.
[8] Fu H, Li H, Dong Y, et al. Segmenting individual tree from TLS point clouds using improved DBSCAN [J]. Forests, 2022, 13(4): 566.
[9] 霍朗宁, 张晓丽. 基于机载LiDAR点云多层聚类的单木信息提取及其精度评价[J]. 林业科学, 2021, 57(1): 85-94. Huo L N, Zhang X L. Individual tree information extraction and accuracy evaluation based on airborne LiDAR point cloud by multilayer clustering method [J]. Scientia Silvae Sinicae, 2021, 57(1): 85-94. (in Chinese)
[10] Dai W, Yang B, Dong Z, et al. A new method for 3D individual tree extraction using multispectral airborne LiDAR point clouds [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 144: 400-411.
[11] 徐嘉淼, 刘如飞, 魏晓东, 等. 一种顾及体元邻域关系的行道树提取方法[J]. 遥感信息, 2020, 35(4): 105-112. Xu J M, Liu R F, Wei X D, et al. A method of border tree extraction considering neighborhood of voxel [J]. Remote Sensing Information, 2020, 35(4): 105-112. (in Chinese)
[12] Husain A, Vaishya R C. An automated approach for street trees detection using mobile laser scanner data [J]. Remote Sensing Applications: Society and Environment, 2020, 20: 100371.
[13] Li L, Li D L, Zhu H H, et al. A dual growing method for the automatic extraction of individual trees from mobile laser scanning data [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 120: 37-52.
[14] 邢涛, 汪献义, 邢艳秋. 基于特征选择的TLS蒙古栎人工林点云分类研究[J]. 中南林业科技大学学报, 2020, 40(3): 1-7. Xing T, Wang X Y, Xing Y Q. Research on point cloud classification of TLS Mongolian oak plantation forest based on feature selection [J]. Journal of Central South University of Forestry & Technology, 2020, 40(3): 1-7. (in Chinese)
[15] 方莉娜, 沈贵熙, 游志龙, 等. 融合点云和多视图的车载激光点云路侧多目标识别[J]. 测绘学报, 2021, 50(11): 1558-1573. Fang L N, Shen G X, Yu Z L, et al. A joint network of point cloud and multiple views for roadside objects recognition from mobile laser point clouds [J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(11): 1558-1573. (in Chinese)
[16] Luo H F, Khoshelham K, Chen C C, et al. Individual tree extraction from urban mobile laser scanning point clouds using deep pointwise direction embedding [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 175: 326-339.
