sudo apt-get install libmatio-dev
Run ./HYFMGPU
with the following parameters:
./HYFMGPU <reference_image.mat> <target_image.mat>
Outputs:
rot_scal
allows generating new target images with specific a scale and angle of rotation for testing the performance of the method.
Use:
./rot_scal <image.mat> <scale> <angle>
The output image is saved in the same directory with the name rot_scal_out.mat
.
Using Santa Barbara Line images:
./HYFMGPU SantaBarbaraLine2013.mat SantaBarbaraLine2014.mat
Using Pavia University image:
./rot_scal PaviaUniversity.mat 2.0 90
./HYFMGPU PaviaUniversity.mat ./rot_scal_out.mat
This algorithm was presented in the paper "GPU Accelerated FFT-based Registration of Hyperspectral Scenes" that is under revision. If you use this program in your research projects, we encourage you to please cite our work:
@article{alvaro2017hyfmgpu,
title = {{GPU} Accelerated {FFT-based} Registration of Hyperspectral Scenes},
journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
volume = {XX},
number = {XX},
year = {XXXX},
pages = {XXXX-XXXX},
author={Ord\'o\~nez, \'Alvaro and Arg{\"u}ello, Francisco and Heras, Dora B.}
}