Bayesian reconstruction of hyperspectral images by using compressed sensing measurements and a local structured prior

Yuri Mejia; Henry Arguello; Facundo Costa; Jean-Yves Tourneret; Hadj Batatia

doi:10.1109/ICASSP.2017.7952730

Bayesian reconstruction of hyperspectral images by using compressed sensing measurements and a local structured prior

Yuri Mejia, Henry Arguello, Facundo Costa, Jean-Yves Tourneret, Hadj Batatia

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Citations (Scopus)

Abstract

This paper introduces a hierarchical Bayesian model for the reconstruction of hyperspectral images using compressed sensing measurements. This model exploits known properties of natural images, promoting the recovered image to be sparse on a selected basis and smooth in the image domain. The posterior distribution of this model is too complex to derive closed form expressions for the estimators of its parameters. Therefore, an MCMC method is investigated to sample this posterior distribution. The resulting samples are used to estimate the unknown model parameters and hyperparameters in an unsupervised framework. The results obtained on real data illustrate the improvement in reconstruction quality when compared to some existing techniques.

Original language	English
Title of host publication	2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher	IEEE
Pages	3116-3120
Number of pages	5
ISBN (Electronic)	9781509041176
DOIs	https://doi.org/10.1109/ICASSP.2017.7952730
Publication status	Published - 19 Jun 2017
Event	42nd IEEE International Conference on Acoustics, Speech, and Signal Processing 2017 - New Orleans, United States Duration: 5 Mar 2017 → 9 Mar 2017

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Conference

Conference	42nd IEEE International Conference on Acoustics, Speech, and Signal Processing 2017
Abbreviated title	ICASSP 2017
Country/Territory	United States
City	New Orleans
Period	5/03/17 → 9/03/17

Keywords

Bayesian reconstruction
compressive sampling
Spectral imaging

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2017.7952730

Cite this

Mejia, Y., Arguello, H., Costa, F., Tourneret, J.-Y., & Batatia, H. (2017). Bayesian reconstruction of hyperspectral images by using compressed sensing measurements and a local structured prior. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 3116-3120). (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). IEEE. https://doi.org/10.1109/ICASSP.2017.7952730

Mejia, Yuri ; Arguello, Henry ; Costa, Facundo et al. / Bayesian reconstruction of hyperspectral images by using compressed sensing measurements and a local structured prior. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2017. pp. 3116-3120 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{4a53f356e7e14b4d93f90d5a3ff28b8c,

title = "Bayesian reconstruction of hyperspectral images by using compressed sensing measurements and a local structured prior",

abstract = "This paper introduces a hierarchical Bayesian model for the reconstruction of hyperspectral images using compressed sensing measurements. This model exploits known properties of natural images, promoting the recovered image to be sparse on a selected basis and smooth in the image domain. The posterior distribution of this model is too complex to derive closed form expressions for the estimators of its parameters. Therefore, an MCMC method is investigated to sample this posterior distribution. The resulting samples are used to estimate the unknown model parameters and hyperparameters in an unsupervised framework. The results obtained on real data illustrate the improvement in reconstruction quality when compared to some existing techniques.",

keywords = "Bayesian reconstruction, compressive sampling, Spectral imaging",

author = "Yuri Mejia and Henry Arguello and Facundo Costa and Jean-Yves Tourneret and Hadj Batatia",

year = "2017",

month = jun,

day = "19",

doi = "10.1109/ICASSP.2017.7952730",

language = "English",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "IEEE",

pages = "3116--3120",

booktitle = "2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

address = "United States",

note = "42nd IEEE International Conference on Acoustics, Speech, and Signal Processing 2017, ICASSP 2017 ; Conference date: 05-03-2017 Through 09-03-2017",

}

Mejia, Y, Arguello, H, Costa, F, Tourneret, J-Y & Batatia, H 2017, Bayesian reconstruction of hyperspectral images by using compressed sensing measurements and a local structured prior. in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, IEEE, pp. 3116-3120, 42nd IEEE International Conference on Acoustics, Speech, and Signal Processing 2017, New Orleans, Louisiana, United States, 5/03/17. https://doi.org/10.1109/ICASSP.2017.7952730

Bayesian reconstruction of hyperspectral images by using compressed sensing measurements and a local structured prior. / Mejia, Yuri; Arguello, Henry; Costa, Facundo et al.
2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2017. p. 3116-3120 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Bayesian reconstruction of hyperspectral images by using compressed sensing measurements and a local structured prior

AU - Mejia, Yuri

AU - Arguello, Henry

AU - Costa, Facundo

AU - Tourneret, Jean-Yves

AU - Batatia, Hadj

PY - 2017/6/19

Y1 - 2017/6/19

N2 - This paper introduces a hierarchical Bayesian model for the reconstruction of hyperspectral images using compressed sensing measurements. This model exploits known properties of natural images, promoting the recovered image to be sparse on a selected basis and smooth in the image domain. The posterior distribution of this model is too complex to derive closed form expressions for the estimators of its parameters. Therefore, an MCMC method is investigated to sample this posterior distribution. The resulting samples are used to estimate the unknown model parameters and hyperparameters in an unsupervised framework. The results obtained on real data illustrate the improvement in reconstruction quality when compared to some existing techniques.

AB - This paper introduces a hierarchical Bayesian model for the reconstruction of hyperspectral images using compressed sensing measurements. This model exploits known properties of natural images, promoting the recovered image to be sparse on a selected basis and smooth in the image domain. The posterior distribution of this model is too complex to derive closed form expressions for the estimators of its parameters. Therefore, an MCMC method is investigated to sample this posterior distribution. The resulting samples are used to estimate the unknown model parameters and hyperparameters in an unsupervised framework. The results obtained on real data illustrate the improvement in reconstruction quality when compared to some existing techniques.

KW - Bayesian reconstruction

KW - compressive sampling

KW - Spectral imaging

UR - http://www.scopus.com/inward/record.url?scp=85023769815&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2017.7952730

DO - 10.1109/ICASSP.2017.7952730

M3 - Conference contribution

AN - SCOPUS:85023769815

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 3116

EP - 3120

BT - 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - IEEE

T2 - 42nd IEEE International Conference on Acoustics, Speech, and Signal Processing 2017

Y2 - 5 March 2017 through 9 March 2017

ER -

Mejia Y, Arguello H, Costa F, Tourneret JY, Batatia H. Bayesian reconstruction of hyperspectral images by using compressed sensing measurements and a local structured prior. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. 2017. p. 3116-3120. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2017.7952730

Bayesian reconstruction of hyperspectral images by using compressed sensing measurements and a local structured prior

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this