DocumentCode
3198785
Title
Improved covariance matrices for point target detection in hyperspectral data
Author
Sofer, Y. ; Geva, E. ; Rotman, S.R.
Author_Institution
Dep. of Electr. & Comput. Eng., Ben-Gurion Univ. of the Negev, Beer-Sheva, Israel
fYear
2009
fDate
9-11 Nov. 2009
Firstpage
1
Lastpage
4
Abstract
Algorithms for point target detection in hyperspectral images use the inverse covariance matrix in order to separate a detected pixel from it surrounding noise. The inverse covariance matrix can be implemented from all the pixels or from the close surroundings of the examined pixel. We compare the different methods and conclude which method brings the best results.
Keywords
covariance matrices; geophysical image processing; remote sensing; hyperspectral data; hyperspectral images; inverse covariance matrix; point target detection; Background noise; Biomedical imaging; Covariance matrix; Eigenvalues and eigenfunctions; Histograms; Hyperspectral imaging; Matched filters; Object detection; Pixel; Signal to noise ratio;
fLanguage
English
Publisher
ieee
Conference_Titel
Microwaves, Communications, Antennas and Electronics Systems, 2009. COMCAS 2009. IEEE International Conference on
Conference_Location
Tel Aviv
Print_ISBN
978-1-4244-3985-0
Type
conf
DOI
10.1109/COMCAS.2009.5385980
Filename
5385980
Link To Document