Hierarchical Fine Extraction Method of Street Tree Information from Mobile LiDAR Point Cloud Data

Abstract

The classification and extraction of street tree geometry information in road scenes is crucial in urban forest biomass statistics and road safety. To address the problem of 3D fine extraction of street trees in complex road scenes, this paper designs and investigates a method for extracting street tree geometry and forest parameters from vehicle-mounted LiDAR point clouds in road scenes based on a Gaussian distributed regional growth algorithm and Voronoi range constraints. Firstly, a large number of non-tree and other noise points, such as ground points, buildings, shrubs and vehicle points, are filtered by applying multi-geometric features; then, the main trunk of the street tree is extracted based on the vertical linear features of the tree and the region growth algorithm based on Gaussian distribution; secondly, a Voronoi polygon constraint is established to segment the single tree canopy region with the main trunk center of mass; finally, based on the extracted locations of the street trees and their 3D points, the tree growth parameters of individual trees are obtained for informative management and biomass estimation by combining geometric statistical methods. In this paper, the experimental data from vehicle-borne LiDAR point clouds of different typical areas were selected to verify that the proposed Gaussian-distributed regional growth algorithm can achieve fine classification and extraction of tree growth parameters for different types of roadside trees, with accuracy, recall and F1 values reaching 96.34%, 97.22% and 96.45%, respectively. This research method can be used for the extraction of 3D fine classification of street trees in complex road environments, which in turn can provide support for the safety management of traffic facilities and forest biomass estimation in urban environments.

A Review of Dynamic Object Filtering in SLAM Based on 3D LiDAR

“…The point cloud represents the spatial layout of the environment, which can be used to build a map and localize the robot within it. As research in the field of 3D LiDAR continues to advance [5,6], the exploration of SLAM technology based on this has gained significant momentum across various domains [7][8][9][10][11][12][13][14][15][16][17]. Consequently, numerous remarkable algorithms have been developed [18][19][20][21][22][23][24][25][26], with the most widely adopted ones being LOAM(LiDAR Odometry and Mapping) [20], and its various variants [2,21,22]; LIO (LiDAR-Inertial Odometry) [23,24,27,28]; and R3LIVE [25,26].…”

Three-Dimensional Modeling and Visualization of Single Tree LiDAR Point Cloud Using Matrixial Form

“…Data subsets describing individual trees can be extracted from LiDAR data [38,50,52] for modeling purposes. Tree models are generated from LiDAR point clouds with the use of clustering algorithms in machine learning that extract geometric properties of tree trunks, branches, and canopies [53,60].…”

“…Solutions for modeling individual leaves have also been proposed [54,57]. Voronoi diagrams have been used to extract individual trees from point clouds, and tree canopies have been extracted with region growing algorithms and grouping algorithms [38]. Zhu et al [55] concluded that models of the structure and shape of trees, branches, and canopies are not always satisfactory in terms of silhouette and detail.…”

A Weak Sample Optimisation Method for Building Classification in a Semi-Supervised Deep Learning Framework

“…High-spatial-resolution remote sensing data have shown great potential for application in areas such as precision agricultural monitoring [1][2][3], urban and rural regional planning, road traffic management [4,5], high precision navigation maps [6][7][8], environmental disaster assessment [9,10], forestry measurement [11][12][13], and military construction. Buildings, as the main body in urban construction, occupy a more important component in highresolution remote sensing images.…”