RT Journal Article
T1 GPU Accelerated FFT-Based Registration of Hyperspectral Scenes
A1 Ordóñez Iglesias, Álvaro
A1 Argüello Pedreira, Francisco
A1 Blanco Heras, Dora
K1 CUDA
K1 Fourier transforms
K1 GPU
K1 Hyperspectral imaging
K1 Image registration
K1 Remote sensing
AB Registration is a fundamental previous task in many applications of hyperspectrometry. Most of the algorithms developed are designed to work with RGB images and ignore the execution time. This paper presents a phase correlation algorithm on GPU to register two remote sensing hyperspectral images. The proposed algorithm is based on principal component analysis, multilayer fractional Fourier transform, combination of log-polar maps, and peak processing. It is fully developed in CUDA for NVIDIA GPUs. Different techniques such as the efficient use of the memory hierarchy, the use of CUDA libraries, and the maximization of the occupancy have been applied to reach the best performance on GPU. The algorithm is robust achieving speedups in GPU of up to 240.6×
PB IEEE
SN 1939-1404
YR 2017
FD 2017
LK http://hdl.handle.net/10347/17883
UL http://hdl.handle.net/10347/17883
LA eng
NO Ordonez, A., Arguello, F., & Heras, D. (2017). GPU Accelerated FFT-Based Registration of Hyperspectral Scenes. IEEE Journal Of Selected Topics In Applied Earth Observations And Remote Sensing, 10(11), 4869-4878. doi: 10.1109/jstars.2017.2734052
NO This work was supported in part by the Consellería de Cultura, Educacion e Ordenación Universitaria under Grant GRC2014/008 and Grant ED431G/08 and in part by the Ministry of Education, Culture and Sport, Government of Spain under Grant TIN2013-41129-P and Grant TIN2016-76373-P. Both are cofunded by the European Regional Development Fund.The work of A. Ordóñez was supported by the Ministry of Education, Culture and Sport, Government of Spain, under an FPU Grant FPU16/03537
DS Minerva
RD 22 abr 2026