DocumentCode
2943312
Title
Fully polarimetric classification accuracy
Author
Ouchi, K. ; Davidson, G. ; Saito, G. ; Ishitsuka, N. ; Mohri, K. ; Uratsuka, S.
Author_Institution
Dept. of Environ. Syst. Eng., Kochi Univ. of Technol., Japan
Volume
7
fYear
2003
fDate
21-25 July 2003
Firstpage
4465
Abstract
Assuming that polarimetric data is entirely described by the underlying complex covariance matrix, this paper gives expressions for the maximum likelihood classification accuracy, and applies these to real data. This assumes negligible interclass environmental variation and a homogeneous image structure which is overly simplistic. By including a model of environmental variation, more realistic results may be possible.
Keywords
covariance matrices; geophysical techniques; radar polarimetry; radar theory; spaceborne radar; synthetic aperture radar; SAR; covariance matrix; environmental variation; homogeneous image structure; maximum likelihood classification accuracy; polarimetric classification accuracy; synthetic aperture radar; Agricultural engineering; Agriculture; Bayesian methods; Covariance matrix; Data engineering; Ecosystems; Layout; Spatial resolution; Statistics; Systems engineering and theory;
fLanguage
English
Publisher
ieee
Conference_Titel
Geoscience and Remote Sensing Symposium, 2003. IGARSS '03. Proceedings. 2003 IEEE International
Print_ISBN
0-7803-7929-2
Type
conf
DOI
10.1109/IGARSS.2003.1295548
Filename
1295548
Link To Document