Title :
Fast GPU algorithms for endmember extraction from hyperspectral images
Author :
ElMaghrbay, Mahmoud ; Ammar, Reda ; Rajasekaran, Sanguthevar
Author_Institution :
CSE Dept., Univ. of Connecticut, Storrs, CT, USA
Abstract :
The N-FINDER algorithm is widely used for endmember extraction from hyperspectral images. One of the disadvantages of N-FINDER is that its sequential implementations have long run times due to their relatively large computational complexity. A fast parallel version of N-FINDER is developed in this paper. This version combined with the use of Hyperspectral Image Reduction for Endmember Extraction technique (HIREE) provides an algorithm that is 8 times faster than the original N-FINDER sequential algorithm.
Keywords :
feature extraction; graphics processing units; image processing; HIREE; N-FINDER sequential algorithm; endmember extraction; fast GPU algorithm; hyperspectral image reduction; parallel version; Computational modeling; Data models; Graphics processing unit; Hyperspectral imaging; Instruction sets; Vectors; Endmember extraction; HIREE; Hyperspectral images; N-FINDER algorithm;
Conference_Titel :
Computers and Communications (ISCC), 2012 IEEE Symposium on
Conference_Location :
Cappadocia
Print_ISBN :
978-1-4673-2712-1
Electronic_ISBN :
1530-1346
DOI :
10.1109/ISCC.2012.6249368
