Home » Source Code » super resolution of hyperspectral images

super resolution of hyperspectral images

miladmiyarrostami
2017-02-18 16:15:22
The author
View(s):
Download(s): 0
Point (s): 1 
Category Category:
super resolutionsuper resolution AllAll

Description

Remote sensing hyperspectral images (HSIs) are


quite often low rank, in the sense that the data belong to


a low dimensional subspace/manifold. This has been recently


exploited for the fusion of low spatial resolution HSI with


high spatial resolution multispectral images in order to obtain


super-resolution HSI. Most approaches adopt an unmixing or


a matrix factorization perspective. The derived methods have


led to state-of-the-art results when the spectral information


lies in a low-dimensional subspace/manifold. However, if the


subspace/manifold dimensionality spanned by the complete data


set is large, i.e., larger than the number of multispectral bands,


the performance of these methods mainly decreases because the


underlying sparse regression problem is severely ill-posed. In this


paper, we propose a local approach to cope with this difficulty.


Fundamentally, we exploit the fact that real world HSIs are


locally low rank, that is, pixels acquired from a given spatial




Manuscript received January 6, 2015; revised June 29, 2015; accepted


October 15, 2015. Date of publication October 30, 2015; date of current


version December 9, 2015. This work was supported by the European


Research Council (Programme FP7/20072013) through the DECODA Project


under Grant 2012-ERC-AdG-320594. The work of G. Licciardi was supported


by the French National Research Agency through the XIMRI Project under


Grant ANR-BLAN-SIMI2-LS-101019-6-01. The work of M. Simões was


supported by the Portuguese Science and Technology Foundation under


Grant SFRH/BD/87693/2012. The work of J. M. Bioucas-Dias was supported


in part by the Portuguese Science and Technology Foundation under


Project PTDC/EEIPRO/1470/2012 and Grant UID/EEA/50008/2013, and in


part by the European Research Council through the CHESS Project under


Grant 2012-ERC-AdG-320684. The associate editor coordinating the review


of this manuscript and approving it for publication was Prof. Peter Tay.


M. A. Veganzones is with the Grenoble Images Parole Signal Automatique


Laboratory, Department of Image and Signal, CNRS, Saint-Martin-d’Hères


F-38402, France (e-mail: miguel-angel.veganzones@gipsa-lab.fr).


G. Licciardi is with the Grenoble Images Parole Signal Automatique Laboratory,


Department of Image and Signal, Grenoble Institute of Technology,


Saint-Martin-d’Hères F-38402, France (e-mail: giorgio.licciardi@gipsa-lab.fr).


M. Simões is with the Grenoble Images Parole Signal Automatique Laboratory,


Department of Image and Signal, Grenoble Institute of Technology,


Saint-Martin-d’Hères F-38402, France, and also with the Instituto de Telecomunicações


and the Instituto Superior Técnico, Universidade de Lisboa,


Lisbon 1049-001, Portugal (e-mail: miguel.simoes@gipsa-lab.fr).


N. Yokoya is with the Department of Advanced Interdisciplinary Studies,


The University of Tokyo, Tokyo 113-8654, Japan (e-mail: yokoya@sal.


rcast.u-tokyo.ac.jp).


J. M. Bioucas-Dias is with the Instituto de Telecomunicações and the


Instituto Superior Técnico, Universidade de Lisboa, Lisbon 1049-001, Portugal


(e-mail: bioucas@lx.it.pt).


J. Chanussot is with the Grenoble Images Parole Signal Automatique Laboratory,


Department of Image and Signal, Grenoble Institute of Technology,


Saint-Martin-d’Hères F-38402, France, and also with the Faculty of Electrical


and Computer Engineering, University of Iceland, Reykjavik 101, Iceland


(e-mail: jocelyn.chanussot@gipsa-lab.fr).


Color versions of one or more of the figures in this paper are available


online at http://ieeexplore.ieee.org.


Digital Object Identifier 10.1109/TIP.2015.2496263



neighborhood span a very low-dimensional subspace/manifold,


i.e., lower or equal than the number of multispectral bands.


Thus, we propose to partition the image into patches and solve


the data fusion problem independently for each patch. This way,


in each patch the subspace/manifold dimensionality is low


enough, such that the problem is not ill-posed anymore. We propose


two alternative approaches to define the hyperspectral superresolution


through local dictionary learning using endmember


induction algorithms. We also explore two alternatives to define


the local regions, using sliding windows and binary partition


trees. The effectiveness of the proposed approaches is illustrated


with synthetic and semi real data.




Sponsored links

File list

Tips: You can preview the content of files by clicking file names^_^
Name Size Date
Sponsored links

Comments

(Add your comment, get 0.1 Point)
Minimum:15 words, Maximum:160 words
  • 1
  • Page 1
  • Total 1

super resolution of hyperspectral images (3.67 MB)

Need 1 Point(s)
Your Point (s)

Your Point isn't enough.

Get 22 Point immediately by PayPal

Point will be added to your account automatically after the transaction.

More(Debit card / Credit card / PayPal Credit / Online Banking)

Submit your source codes. Get more Points

LOGIN

Don't have an account? Register now
Need any help?
Mail to: support@codeforge.com

切换到中文版?

CodeForge Chinese Version
CodeForge English Version

Where are you going?

^_^"Oops ...

Sorry!This guy is mysterious, its blog hasn't been opened, try another, please!
OK

Warm tip!

CodeForge to FavoriteFavorite by Ctrl+D