Individual tree extraction from terrestrial laser scanning data via graph pathing

作     者：Di Wang Xinlian Liang Gislain II Mofack Olivier Martin-Ducup Di Wang;Xinlian Liang;Gislain II Mofack;Olivier Martin-Ducup

作者机构：Department of Remote Sensing Science and TechnologySchool of Electronic EngineeringXidian University710077 Xi’anChina State Key Laboratory of Information Engineering in Surveying Mapping and Remote SensingWuhan University430079 WuhanChina Department of Remote Sensing and PhotogrammetryFinnish Geospatial Research Institute02430 MasalaFinland Plant Systematics and Ecology LaboratoryHigher Teacher’s Training CollegeUniversity of Yaounde IBP 337 YaoundeCameroon AMAPUniv MontpellierIRDCNRSCIRADINRAEF-34000 MontpellierFrance 

出 版 物：《Forest Ecosystems》 (森林生态系统（英文版）)

年 卷 期：2021年第8卷第4期

页      面：903-913页

核心收录：

学科分类：080901[工学-物理电子学] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 080401[工学-精密仪器及机械] 09[农学] 0903[农学-农业资源与环境] 0804[工学-仪器科学与技术] 0803[工学-光学工程] 

基　　金：partially funded by the Scientific Research Foundation of Xidian University part of 3DForMod project(ANR-17-EGAS-0002-01)funded in the frame of the JPI FACCE ERA-GAS call funded under European Union’s Horizon 2020 research and innovation program(grant agreement No.696356) 

主　　题：Point cloud Segmentation Tree extraction Graph pathing 

摘      要：Background:Individual tree extraction from terrestrial laser scanning(TLS)data is a prerequisite for tree-scale estimations of forest biophysical *** task currently is undertaken through laborious and time-consuming manual assistance and quality *** study presents a new fully automatic approach to extract single trees from large-area TLS *** data-driven method operates exclusively on a point cloud graph by path finding,which makes our method computationally efficient and universally applicable to data from various forest ***:We demonstrated the proposed method on two openly available ***,we achieved state-of-the-art performance on locating single trees on a benchmark dataset by significantly improving the mean accuracy by over 10% especially for difficult forest ***,we successfully extracted 270 trees from one hectare temperate *** validation resulted in a mean Intersection over Union(mIoU)of 0.82 for single crown segmentation,which further led to a relative root mean square error(RMSE%)of 21.2% and 23.5% for crown area and tree volume estimations,***:Our method allows automated access to individual tree level information from TLS point *** proposed method is free from restricted assumptions of forest *** is also computationally efficient with an average processing time of several seconds for one million *** is expected and hoped that our method would contribute to TLS-enabled wide-area forest qualifications,ranging from stand volume and carbon stocks modelling to derivation of tree functional traits as part of the global ecosystem understanding.