Online Deconvolution for Industrial Hyperspectral Imaging Systems

Song, Yingying; Djermoune, El‐Hadi; Chen, Jie; Richard, Cédric; Brie, David

doi:10.1137/18m1177640

Cited by 9 publications

(6 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al [163] proposed to perform deconvolution filter computations in the same support as the PSF, so that large matrix manipulations are avoided without memory limitations. Song et al [164] derived a slidingblock zero-attracting least mean square algorithm allowing the fast slice-by-slice online HSIs deconvolution. Avagian et al [165] implemented the Lucy-Richardson HSI deconvolution algorithm accelerated by FPGA.…”

Section: Interesting Extensions 1) Joint With Other Tasksmentioning

confidence: 99%

Image Restoration for Remote Sensing: Overview and Toolbox

Rasti¹,

Chen²,

Dalsasso³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper is under review in GRSM. Remote sensing provides valuable information about objects or areas from a distance in either active (e.g., RADAR and LiDAR) or passive (e.g., multispectral and hyperspectral) modes. The quality of data acquired by remotely sensed imaging sensors (both active and passive) is often degraded by a variety of noise types and artifacts. Image restoration, which is a vibrant field of research in the remote sensing community, is the task of recovering the true unknown image from the degraded observed image. Each imaging sensor induces unique noise types and artifacts into the observed image. This fact has led to the expansion of restoration techniques in different paths according to each sensor type. This review paper brings together the advances of image restoration techniques with particular focuses on synthetic aperture radar and hyperspectral images as the most active sub-fields of image restoration in the remote sensing community. We, therefore, provide a comprehensive, discipline-specific starting point for researchers at different levels (i.e., students, researchers, and senior researchers) willing to investigate the vibrant topic of data restoration by supplying sufficient detail and references. Additionally, this review paper accompanies a toolbox to provide a platform to encourage interested students and researchers in the field to further explore the restoration techniques and fast-forward the community. The toolboxes are provided in https://github.com/ImageRestorationToolbox.

show abstract

Section: Interesting Extensions 1) Joint With Other Tasksmentioning

confidence: 99%

Image Restoration for Remote Sensing: Overview and Toolbox

Rasti¹,

Chen²,

Dalsasso³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Following the same idea introduced in [9] for online deconvolution, the online joint unmixing-deconvolution is addressed as a sliding block processing. Consider a block of size Q, assumed to be odd, and define:…”

Section: B Online Unmixing and Deconvolutionmentioning

confidence: 99%

“…In [6], the endmembers being assumed to be known, a JUD method with total variation regularization is proposed. The goal of this paper is to propose fast approaches to the JUD problem which can be implemented online using a sliding bock approach similar to the one proposed in [9]. Actually, it should be seen as a preliminary step toward the development of recursive estimators based on LMS (least mean squares).…”

Section: Introductionmentioning

confidence: 99%

Joint unmixing-deconvolution algorithms for hyperspectral images

Song

Djermoune

Brie

et al. 2019

2019 27th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

This paper combines supervised linear unmixing and deconvolution problems to increase the resolution of the abundance maps for industrial imaging systems. The joint unmixing-deconvolution (JUD) algorithm is introduced based on the Tikhonov regularization criterion for offline processing. In order to meet the needs of industrial applications, the proposed JUD algorithm is then extended for online processing by using a block Tikhonov criterion. The performance of JUD is increased by adding a non-negativity constraint which is implemented in a fast way using the quadratic penalty method and fast Fourier transform. The proposed algorithm is then assessed using both simulated and real hyperspectral images.

show abstract

“…Additionally, other methods use Fourier and wavelet transforms to derive effective techniques for the HSI restoration problem [8]. Another direction in this field involves the incorporation of online algorithms, as seen in [9], where a sliding-block regularized Least Mean Squares (LMS) technique is employed.…”

Section: Introductionmentioning

confidence: 99%

Connections Between Deep Equilibrium and Sparse Representation Models With Application to Hyperspectral Image Denoising

Gkillas

Ampeliotis

Berberidis

2023

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

In this paper, we propose a novel methodology for addressing the hyperspectral image deconvolution problem. This problem is highly ill-posed, and thus, requires proper priors (regularizers) to model the inherent spectral-spatial correlations of the HSI signals. To this end, a new optimization problem is formulated, leveraging a learnable regularizer in the form of a neural network. To tackle this problem, an effective solver is proposed using the half quadratic splitting methodology. The derived iterative solver is then expressed as a fixedpoint calculation problem within the Deep Equilibrium (DEQ) framework, resulting in an interpretable architecture, with clear explainability to its parameters and convergence properties with practical benefits. The proposed model is a first attempt to handle the classical HSI degradation problem with different blurring kernels and noise levels via a single deep equilibrium model with significant computational efficiency. Extensive numerical experiments validate the superiority of the proposed methodology over other state-of-the-art methods. This superior restoration performance is achieved while requiring 99.85% less computation time as compared to existing methods.

show abstract

Online Deconvolution for Industrial Hyperspectral Imaging Systems

Cited by 9 publications

References 43 publications

Image Restoration for Remote Sensing: Overview and Toolbox

Image Restoration for Remote Sensing: Overview and Toolbox

Joint unmixing-deconvolution algorithms for hyperspectral images

Connections Between Deep Equilibrium and Sparse Representation Models With Application to Hyperspectral Image Denoising

Contact Info

Product

Resources

About