文献类型：期刊文献

英文题名：Separating Tree Photosynthetic and Non-Photosynthetic Components from Point Cloud Data Using Dynamic Segment Merging

作者：Wang, Di[1] Brunner, Jasmin[1] Ma, Zhenyu[2] Lu, Hao[3] Hollaus, Markus[1] Pang, Yong[2] Pfeifer, Norbert[1]

第一作者：Wang, Di

通信作者：Wang, D[1]

机构：[1]TU Wien, Dept Geodesy & Geoinformat, A-1040 Vienna, Austria;[2]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China;[3]Beijing Forestry Univ, Sch Informat Sci & Technol, Beijing 100083, Peoples R China

年份：2018

卷号：9

期号：5

外文期刊名：FORESTS

收录：;EI(收录号：20182005186466);Scopus(收录号：2-s2.0-85046678466);WOS:【SCI-EXPANDED(收录号:WOS:000435193700027)】；

基金：Special thanks are due to referees for their constructive reviews that improved the manuscript significantly. The study was supported by the project "The influence of Biomass and its change on landSLIDE activity" (BioSLIDE) within the research program Earth System Sciences (ESS) of the Austrian Academy of Science (Osterreichische Akademie der Wissenschaften, OAW). Partial fund was jointly provided by the OAW, the Ministry of Education, Youth and Sports of the Czech Republic and the Slovak Research and Development Agency under the contract No. DS-2016-0040. The authors also thank the Austrian Research Promotion Agency (FFG) for providing financial support via the project No. 860021.

语种：英文

外文关键词：Laser scanning; dynamic segmentation; point classification; pattern recognition; wood-leaf classification

摘要：Many biophysical forest properties such as wood volume and leaf area index (LAI) require prior knowledge on either photosynthetic or non-photosynthetic components. Laser scanning appears to be a helpful technique in nondestructively quantifying forest structures, as it can acquire an accurate three-dimensional point cloud of objects. In this study, we propose an unsupervised geometry-based method named Dynamic Segment Merging (DSM) to identify non-photosynthetic components of trees by semantically segmenting tree point clouds, and examining the linear shape prior of each resulting segment. We tested our method using one single tree dataset and four plot-level datasets, and compared our results to a supervised machine learning method. We further demonstrated that by using an optimal neighborhood selection method that involves multi-scale analysis, the results were improved. Our results showed that the overall accuracy ranged from 81.8% to 92.0% with an average value of 87.7%. The supervised machine learning method had an average overall accuracy of 86.4% for all datasets, on account of a collection of manually delineated representative training data. Our study indicates that separating tree photosynthetic and non-photosynthetic components from laser scanning data can be achieved in a fully unsupervised manner without the need of training data and user intervention.