Individual tree segmentation of airborne and UAV LiDAR point clouds based on the watershed and optimized connection center evolution clustering

Abstract Light detection and ranging (LiDAR) data can provide 3D structural information of objects and are ideal for extracting individual tree parameters, and individual tree segmentation (ITS) is a vital step for this purpose. Various ITS methods have been emerging from airborne LiDAR scanning (AL...

Full description

Saved in:
Bibliographic Details
Main Authors: Yi Li, Donghui Xie, Yingjie Wang, Shuangna Jin, Kun Zhou, Zhixiang Zhang, Weihua Li, Wuming Zhang, Xihan Mu, Guangjian Yan
Format: Article
Language:English
Published: Wiley 2023-07-01
Series:Ecology and Evolution
Subjects:
Online Access:https://doi.org/10.1002/ece3.10297
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850038725642289152
author Yi Li
Donghui Xie
Yingjie Wang
Shuangna Jin
Kun Zhou
Zhixiang Zhang
Weihua Li
Wuming Zhang
Xihan Mu
Guangjian Yan
author_facet Yi Li
Donghui Xie
Yingjie Wang
Shuangna Jin
Kun Zhou
Zhixiang Zhang
Weihua Li
Wuming Zhang
Xihan Mu
Guangjian Yan
author_sort Yi Li
collection DOAJ
description Abstract Light detection and ranging (LiDAR) data can provide 3D structural information of objects and are ideal for extracting individual tree parameters, and individual tree segmentation (ITS) is a vital step for this purpose. Various ITS methods have been emerging from airborne LiDAR scanning (ALS) or unmanned aerial vehicle LiDAR scanning (ULS) data. Here, we propose a new individual tree segmentation method, which couples the classical and efficient watershed algorithm (WS) and the newly developed connection center evolution (CCE) clustering algorithm in pattern recognition. The CCE is first used in ITS and comprehensively optimized by considering tree structure and point cloud characteristics. Firstly, the amount of data is greatly reduced by mean shift voxelization. Then, the optimal clustering scale is automatically determined by the shapes in the projection of three different directions. We select five forest plots in Saihanba, China and 14 public plots in Alpine region, Europe with ULS or ALS point cloud densities from 11 to 3295 pts/m2. Eleven ITS methods were used for comparison. The accuracy of tree top detection and tree height extraction is estimated by five and two metrics, respectively. The results show that the matching rate (Rmatch) of tree tops is up to 0.92, the coefficient of determination (R2) of tree height estimation is up to .94, and the minimum root mean square error (RMSE) is 0.6 m. Our method outperforms the other methods especially in the broadleaf forests plot on slopes, where the five evaluation metrics for tree top detection outperformed the other algorithms by at least 11% on average. Our ITS method is both robust and efficient and has the potential to be used especially in coniferous forests to extract the structural parameters of individual trees for forest management, carbon stock estimation, and habitat mapping.
format Article
id doaj-art-d12262243b444f83b6cd60c47a20e913
institution DOAJ
issn 2045-7758
language English
publishDate 2023-07-01
publisher Wiley
record_format Article
series Ecology and Evolution
spelling doaj-art-d12262243b444f83b6cd60c47a20e9132025-08-20T02:56:31ZengWileyEcology and Evolution2045-77582023-07-01137n/an/a10.1002/ece3.10297Individual tree segmentation of airborne and UAV LiDAR point clouds based on the watershed and optimized connection center evolution clusteringYi Li0Donghui Xie1Yingjie Wang2Shuangna Jin3Kun Zhou4Zhixiang Zhang5Weihua Li6Wuming Zhang7Xihan Mu8Guangjian Yan9State Key Laboratory of Remote Sensing Science, Beijing Engineering Research Center for Global Land Remote Sensing Products Beijing Normal University Beijing ChinaState Key Laboratory of Remote Sensing Science, Beijing Engineering Research Center for Global Land Remote Sensing Products Beijing Normal University Beijing ChinaCESBIO University of Toulouse Toulouse FranceState Key Laboratory of Remote Sensing Science, Beijing Engineering Research Center for Global Land Remote Sensing Products Beijing Normal University Beijing ChinaState Key Laboratory of Remote Sensing Science, Beijing Engineering Research Center for Global Land Remote Sensing Products Beijing Normal University Beijing ChinaState Key Laboratory of Remote Sensing Science, Beijing Engineering Research Center for Global Land Remote Sensing Products Beijing Normal University Beijing ChinaState Key Laboratory of Remote Sensing Science, Beijing Engineering Research Center for Global Land Remote Sensing Products Beijing Normal University Beijing ChinaSchool of Geospatial Engineering and Science Sun Yat‐Sen University Zhuhai ChinaState Key Laboratory of Remote Sensing Science, Beijing Engineering Research Center for Global Land Remote Sensing Products Beijing Normal University Beijing ChinaState Key Laboratory of Remote Sensing Science, Beijing Engineering Research Center for Global Land Remote Sensing Products Beijing Normal University Beijing ChinaAbstract Light detection and ranging (LiDAR) data can provide 3D structural information of objects and are ideal for extracting individual tree parameters, and individual tree segmentation (ITS) is a vital step for this purpose. Various ITS methods have been emerging from airborne LiDAR scanning (ALS) or unmanned aerial vehicle LiDAR scanning (ULS) data. Here, we propose a new individual tree segmentation method, which couples the classical and efficient watershed algorithm (WS) and the newly developed connection center evolution (CCE) clustering algorithm in pattern recognition. The CCE is first used in ITS and comprehensively optimized by considering tree structure and point cloud characteristics. Firstly, the amount of data is greatly reduced by mean shift voxelization. Then, the optimal clustering scale is automatically determined by the shapes in the projection of three different directions. We select five forest plots in Saihanba, China and 14 public plots in Alpine region, Europe with ULS or ALS point cloud densities from 11 to 3295 pts/m2. Eleven ITS methods were used for comparison. The accuracy of tree top detection and tree height extraction is estimated by five and two metrics, respectively. The results show that the matching rate (Rmatch) of tree tops is up to 0.92, the coefficient of determination (R2) of tree height estimation is up to .94, and the minimum root mean square error (RMSE) is 0.6 m. Our method outperforms the other methods especially in the broadleaf forests plot on slopes, where the five evaluation metrics for tree top detection outperformed the other algorithms by at least 11% on average. Our ITS method is both robust and efficient and has the potential to be used especially in coniferous forests to extract the structural parameters of individual trees for forest management, carbon stock estimation, and habitat mapping.https://doi.org/10.1002/ece3.10297airborne LiDAR scanningconnection center evolutionindividual tree segmentationunmanned aerial vehicle LiDAR scanningwatershed
spellingShingle Yi Li
Donghui Xie
Yingjie Wang
Shuangna Jin
Kun Zhou
Zhixiang Zhang
Weihua Li
Wuming Zhang
Xihan Mu
Guangjian Yan
Individual tree segmentation of airborne and UAV LiDAR point clouds based on the watershed and optimized connection center evolution clustering
Ecology and Evolution
airborne LiDAR scanning
connection center evolution
individual tree segmentation
unmanned aerial vehicle LiDAR scanning
watershed
title Individual tree segmentation of airborne and UAV LiDAR point clouds based on the watershed and optimized connection center evolution clustering
title_full Individual tree segmentation of airborne and UAV LiDAR point clouds based on the watershed and optimized connection center evolution clustering
title_fullStr Individual tree segmentation of airborne and UAV LiDAR point clouds based on the watershed and optimized connection center evolution clustering
title_full_unstemmed Individual tree segmentation of airborne and UAV LiDAR point clouds based on the watershed and optimized connection center evolution clustering
title_short Individual tree segmentation of airborne and UAV LiDAR point clouds based on the watershed and optimized connection center evolution clustering
title_sort individual tree segmentation of airborne and uav lidar point clouds based on the watershed and optimized connection center evolution clustering
topic airborne LiDAR scanning
connection center evolution
individual tree segmentation
unmanned aerial vehicle LiDAR scanning
watershed
url https://doi.org/10.1002/ece3.10297
work_keys_str_mv AT yili individualtreesegmentationofairborneanduavlidarpointcloudsbasedonthewatershedandoptimizedconnectioncenterevolutionclustering
AT donghuixie individualtreesegmentationofairborneanduavlidarpointcloudsbasedonthewatershedandoptimizedconnectioncenterevolutionclustering
AT yingjiewang individualtreesegmentationofairborneanduavlidarpointcloudsbasedonthewatershedandoptimizedconnectioncenterevolutionclustering
AT shuangnajin individualtreesegmentationofairborneanduavlidarpointcloudsbasedonthewatershedandoptimizedconnectioncenterevolutionclustering
AT kunzhou individualtreesegmentationofairborneanduavlidarpointcloudsbasedonthewatershedandoptimizedconnectioncenterevolutionclustering
AT zhixiangzhang individualtreesegmentationofairborneanduavlidarpointcloudsbasedonthewatershedandoptimizedconnectioncenterevolutionclustering
AT weihuali individualtreesegmentationofairborneanduavlidarpointcloudsbasedonthewatershedandoptimizedconnectioncenterevolutionclustering
AT wumingzhang individualtreesegmentationofairborneanduavlidarpointcloudsbasedonthewatershedandoptimizedconnectioncenterevolutionclustering
AT xihanmu individualtreesegmentationofairborneanduavlidarpointcloudsbasedonthewatershedandoptimizedconnectioncenterevolutionclustering
AT guangjianyan individualtreesegmentationofairborneanduavlidarpointcloudsbasedonthewatershedandoptimizedconnectioncenterevolutionclustering