Skip to main navigation Skip to search Skip to main content

L0 Gradient Regularized Low-Rank Tensor Model for Hyperspectral Image Denoising

  • Harbin Institute of Technology
  • Université Grenoble Alpes

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Spatial spectral total variation has been widely used in the hyperspectral image (HSI) denoising algorithms. However, the total variation norm only penalizes the gradient magnitudes of HSIs, which may influence the recovery of denoised image edges. In this paper, we proposed a new l0 gradient regularized low-rank tensor model for removing HSI mixed noises. The low-rank tensor Tucker decomposition is applied for recovering the clean HSI part by using the HSI global correlation. The l0 gradient regularization controls the number of non-zero gradients directly and is designed to explore the spatial-spectral property of hyperspectral images and preserve important image features. The optimization problem is solved by the Augmented Lagrange Multiplier (ALM) method efficiently. The real-world data experiment demonstrates the better performance of our method.

Original languageEnglish
Title of host publication2019 10th Workshop on Hyperspectral Imaging and Signal Processing
Subtitle of host publicationEvolution in Remote Sensing, WHISPERS 2019
PublisherIEEE Computer Society
ISBN (Electronic)9781728152943
DOIs
StatePublished - Sep 2019
Event10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2019 - Amsterdam, Netherlands
Duration: 24 Sep 201926 Sep 2019

Publication series

NameWorkshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing
Volume2019-September
ISSN (Print)2158-6276

Conference

Conference10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2019
Country/TerritoryNetherlands
CityAmsterdam
Period24/09/1926/09/19

Keywords

  • ALM
  • HSI denoising
  • l0 gradient
  • low-rank tensor model
  • spatial-spectral property

Fingerprint

Dive into the research topics of 'L0 Gradient Regularized Low-Rank Tensor Model for Hyperspectral Image Denoising'. Together they form a unique fingerprint.

Cite this