Title
Adaptive thematic object extraction from remote sensing image based on spectral matching.
Abstract
An adaptive extraction method based on spectral matching is proposed to extract thematic object completely and accurately from remote sensing image.The algorithm first selects the endmember of thematic object,and use spectral matching method to get the matching index.Then,histogram threshold based auto-segmentation method is used to initially separate thematic object from background.Subsequently,thematic object pixels are searched out and taken as seed points to proceed region growing to gain the local area of thematic object.Lastly,the boundary of the local area is searched and the iterative classification within the local area is employed to precisely extract the precise partition of thematic object.Experiments on ETM+ image to extract water and bareland are employed here.Comparison with maximum likelihood classification and support vector machine(SVM) classification verifies the effectiveness and commonality of the method.
Year
DOI
Venue
2012
10.1016/j.jag.2012.05.012
International Journal of Applied Earth Observation and Geoinformation
Keywords
Field
DocType
Thematic object extraction,Spectral matching,Adaptive,Remote sensing
Spatial analysis,Endmember,Remote sensing,Image based,Remote sensing application,Thematic map,Artificial intelligence,Spectral representation,Geography,Computer vision,Pattern recognition,Support vector machine,Spectral matching
Journal
Volume
Issue
ISSN
19
03
0303-2434
Citations 
PageRank 
References 
0
0.34
5
Authors
5
Name
Order
Citations
PageRank
Cheng Qiao100.34
Jian-Cheng Luo29920.75
Zhanfeng Shen36812.60
Zhiwen Zhu44311.61
Dongping Ming512.38