Diferenzas

Isto amosa as diferenzas entre a revisión seleccionada e a versión actual da páxina.

Enlazar a esta vista de comparación

Both sides previous revisionPrevious revision
Next revision
Previous revision
hiperespectral:hyfm-reg [2016/11/03 09:59] – [Hyperspectral Fourier-Mellin algorithm (HYFM)] alvaro.ordonezhiperespectral:hyfm-reg [2017/11/10 10:47] (actual) – [Fourier–Mellin registration of two hyperspectral images (HYFM)] alvaro.ordonez
Liña 1: Liña 1:
-====== Hyperspectral Fourier-Mellin algorithm (HYFM) ====== +====== FourierMellin registration of two hyperspectral images (HYFM) ====== 
-Experimental results related to the paper **Fourier-Mellin registration of two hyperspectral images** by Álvaro Ordóñez, Francisco Argüello, and Dora B.,  +Experimental results related to the paper [[http://dx.doi.org/10.1080%2F01431161.2017.1292071|Fourier-Mellin registration of two hyperspectral images]] by Álvaro Ordóñez, Francisco Argüello, and Dora B. Heraspublished in International Journal of Remote Sensing.
-that it is under revision. +
 ===== Abstract ===== ===== Abstract =====
-Hyperspectral images contain a great amount of information which can be used to more robustly register such images. In this paper, we present a phase correlation method to register two hyperspectral images that takes into account their multiband structure. The proposed method is based on principal component analysis, multilayerfractional Fourier transform, combination of log-polar maps, and peak processing. The combination of maps is intended to highlight some peaks in the log-polar map using information from different bands. The method is robust and has been successfully tested for any rotation angle with commonly used hyperspectral scenes in remote sensing for scales up to 7.5× and with pairs of hyperspectral images taken on different dates by the AVIRIS sensor for scales up to 6.0×.+Hyperspectral images contain a great amount of information which can be used to more robustly register such images. In this article, we present a phase correlation method to register two hyperspectral images that takes into account their multiband structure. The proposed method is based on principal component analysis, the multilayer fractional Fourier transform, combination of log-polar maps, and peak processing. The combination of maps is aimed at highlighting some peaks in the log-polar map using information from different bands. The method is robust and has been successfully tested for any rotation angle with commonly used hyperspectral scenes in remote sensing for scales of up to 7.5× and with pairs of hyperspectral images taken on different dates by the Airborne Visible/Infrared Imaging Spectrometer (AVIRISsensor for scales of up to 6.0×.
  
 ===== Downloads ===== ===== Downloads =====
Liña 10: Liña 8:
 Compiled program to register two hyperspectral images. Compiled program to register two hyperspectral images.
  
-  * HYFM algorithm: {{:hiperespectral:hyfm-reg.zip|}}+  * HYFM algorithm: {{ :hiperespectral:hyfm-reg.zip |}} 
 + 
 +=== Images === 
 + 
 +All images used in the paper are available in [[https://gitlab.citius.usc.es/hiperespectral/RegistrationRepository|Registration Repository]] 
 + 
 +===== Example ===== 
 + 
 +{{ :hiperespectral:registration_example.png?direct&600 |}}
  
-=== Datasets === +Example of registration process(a) original or reference image, (b) target image (central region of the original image scaled by 5.5× and rotated 45 degrees), and (c) result of the registration process showing the superposition of the reference and target image correctly registered.
-  * Commonly used hyperspectral datasets from Universidad del Pais Vasco[[http://www.ehu.es/ccwintco/index.php?title=Hyperspectral_Remote_Sensing_Scenes|www.ehu.es]] +
-  * Pairs of datasets taken on different dates from AVIRIS NASA: [[http://actualizar.esta.url.es|ACTUALIZAR ISTO]]+
  
 ===== License ===== ===== License =====
  
 :cc-by-nc-sa:   :cc-by-nc-sa: