DOI: 10.1016/j.jag.2014.10.006
Scopus记录号: 2-s2.0-84924425640
论文题名: The effect of atmospheric and topographic correction on pixel-basedimage composites: Improved forest cover detection in mountainenvironments
作者: Vanonckelen S ; , Lhermitte S ; , Rompaey A ; V
刊名: International Journal of Applied Earth Observation and Geoinformation
ISSN: 15698432
出版年: 2015
卷: 35, 期: PB 起始页码: 320
结束页码: 328
语种: 英语
英文关键词: Classification accuracy assessment
; Forest cover mapping
; Landsat
; Mountain areas
; Pixel-based compositing
; Topographic correction
Scopus关键词: accuracy assessment
; artificial intelligence
; atmospheric correction
; classification
; forest cover
; Landsat
; mapping
; maximum likelihood analysis
; mountain environment
; pixel
; topographic effect
; Carpathians
英文摘要: Quantification of forest cover is essential as a tool to stimulate forest management and conservation. Image compositing techniques that sample the most suited pixel from multi-temporal image acquisitions, provide an important tool for forest cover detection as they provide alternatives for missing data dueto cloud cover and data discontinuities. At present, however, it is not clear to which extent forest coverdetection based on compositing can be improved if the source imagery is firstly corrected for topographicdistortions on a pixel-basis. In this study, the results of a pixel compositing algorithm with and withoutpreprocessing topographic correction are compared for a study area covering 9 Landsat footprints inthe Romanian Carpathians based on two different classifiers: Maximum Likelihood (ML) and SupportVector Machine (SVM). Results show that classifier selection has a stronger impact on the classificationaccuracy than topographic correction. Finally, application of the optimal method (SVM classifier withtopographic correction) on the Romanian Carpathian Ecoregion between 1985, 1995 and 2010 shows asteady greening due to more afforestation than deforestation. © 2014 Elsevier B.V. Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/79529
Appears in Collections: 气候变化事实与影响
There are no files associated with this item.
作者单位: Division of Geography, Katholieke Universiteit Leuven, Celestijnenlaan 200E, Heverlee, Belgium
Recommended Citation:
Vanonckelen S,, Lhermitte S,, Rompaey A,et al. The effect of atmospheric and topographic correction on pixel-basedimage composites: Improved forest cover detection in mountainenvironments[J]. International Journal of Applied Earth Observation and Geoinformation,2015-01-01,35(PB)