中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
A Deep Neural Network for the Estimation of Tree Density Based on High-Spatial Resolution Image

文献类型：期刊论文

作者Liu, Tang3,4; Yao, Ling2,4,5; Qin, Jun1,4; Lu, Jiaying1,4; Lu, Ning2,4,5; Zhou, Chenghu3,4
刊名IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
出版日期2021-08-06
页码11
关键词Vegetation Remote sensing Forestry Feature extraction Convolution Kernel Deep learning Deep learning density regression loss function remote sensing tree counting
ISSN号0196-2892
DOI10.1109/TGRS.2021.3101056
通讯作者Yao, Ling(yaoling@lreis.ac.cn)
英文摘要Tree density is a significant parameter for forest. However, it has always been challenging to use remote-sensing techniques to acquire it efficiently and effectively on a large spatial scale. As a matter of fact, tree counting can be regarded as end-to-end density regression, which uses a remote-sensing image as an input and generates a tree density map as an output. Therefore, the tree number can be easily obtained by the summation of density values in an area. To this end, a deep neural network has been constructed to aggregate multiple decoding paths to extract hierarchical features at different encoding stages, in order to merge tree features of multiple scales in remote-sensing images. At the same time, a hybrid loss function has been proposed to effectively guide the network training and enhance the model ability. A tree count dataset consisting of 2400 sample pairs has been constructed for training and validation. When compared with other popular counting networks, it has been found that the proposed network achieved the best results with a relative mean absolute error (rMAE) of 16.72%, a root mean squared error (RMSE) of 77.96, and an R-2 of 0.96, evidencing that this is a promising method for estimating tree numbers on a large spatial scale.
WOS关键词CROWN DELINEATION ; COUNT ; CNN
资助项目National Natural Science Foundation of China[41771380] ; Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)[GML2019ZD0301] ; National Postdoctoral Program for Innovative Talents[BX20200100] ; China Postdoctoral Science Foundation[2020M682628] ; State Key Laboratory of Resources and Environmental Information System ; National Data Sharing Infrastructure of Earth System Science
WOS研究方向Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:000732875600001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China ; Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou) ; National Postdoctoral Program for Innovative Talents ; China Postdoctoral Science Foundation ; State Key Laboratory of Resources and Environmental Information System ; National Data Sharing Infrastructure of Earth System Science
源URL[http://ir.igsnrr.ac.cn/handle/311030/168715]  
专题中国科学院地理科学与资源研究所
通讯作者Yao, Ling
作者单位1.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China
2.Jiangsu Ctr Collaborat Innovat Geog Informat Reso, Nanjing 210023, Peoples R China
3.China Univ Geosci Beijing, Sch Informat Engn, Beijing 100083, Peoples R China
4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China
5.Southern Marine Sci & Engn Guangdong Lab, Guangzhou 511458, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Tang,Yao, Ling,Qin, Jun,et al. A Deep Neural Network for the Estimation of Tree Density Based on High-Spatial Resolution Image[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2021:11.
APA Liu, Tang,Yao, Ling,Qin, Jun,Lu, Jiaying,Lu, Ning,&Zhou, Chenghu.(2021).A Deep Neural Network for the Estimation of Tree Density Based on High-Spatial Resolution Image.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,11.
MLA Liu, Tang,et al."A Deep Neural Network for the Estimation of Tree Density Based on High-Spatial Resolution Image".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2021):11.

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。