Identifying crown areas in an undulating area planted with eucalyptus using unmanned aerial vehicle near-infrared imagery

作者:Kang, J (Kang, Jun)[ 1,2 ] ; Wang, L (Wang, Li)[ 1 ] ; Jia, K (Jia, Kun)[ 3 ] ; Niu, Z (Niu, Zheng)[ 1 ] ; Shakir, M (Shakir, Muhammad)[ 1 ] ; Qiao, HL (Qiao, Hailang)[ 1 ] ; Zhao, X (Zhao, Xin)[ 1 ]

REMOTE SENSING LETTERS

卷: 7  期: 6  页: 561-570

DOI: 10.1080/2150704X.2016.1168947

出版年: 2016

摘要

In this letter, we propose an identification method of tree crown areas for imagery captured by a near-infrared camera on board an unmanned aerial vehicle platform over an undulating Eucalyptus planting area in Guangdong Province, China. The method extracts crown areas by applying mathematical morphology, unsupervised segmentation based on J-value segmentation, local spatial statistics, and Iterative Self-Organizing Data Analysis Technique Algorithm. Two morphology filters and four segmentation scales were compared between densely and sparsely planted plots as well as sunlit and shaded plots. The opening operation by the window size of 9x9 pixel and segmentation by the seed area sized 65x65 pixel achieved the best performance with overall accuracy of 91%, 93%, 89% and 91% in densely sunlit, sparsely sunlit, densely shaded and sparsely shaded plots.

通讯作者地址: Wang, L (通讯作者)

Chinese Acad Sci, Inst Remote & Digital Earth, State Key Lab Remote Sensing Sci, Beijing, Peoples R China.

地址:

[ 1 ] Chinese Acad Sci, Inst Remote & Digital Earth, State Key Lab Remote Sensing Sci, Beijing, Peoples R China

[ 2 ] Univ Chinese Acad Sci, Coll Resources & Environm, Beijing, Peoples R China

[ 3 ] Beijing Normal Univ, State Key Lab Remote Sensing Sci, Sch Geog, Beijing 100875, Peoples R China