Hyperspectral Image Super-Resolution via Local Low-Rank and Sparse Representations
Authors:
- 1 July 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4003-4006
Abstract
Remotely sensed hyperspectral images (HSIs) usually have high spectral resolution but low spatial resolution. A way to increase the spatial resolution of HSIs is to solve a fusion inverse problem, which fuses a low spatial resolution HSI (LR-HSI) with a high spatial resolution multispectral image (HR-MSI) of the same scene. In this paper, we propose a novel HSI super-resolution approach (called LRSR), which formulates the fusion problem as the estimation of a spectral dictionary from the LR-HSI and the respective regression coefficients from both images. The regression coefficients are estimated by formulating a variational regularization problem which promotes local (in the spatial sense) low-rank and sparse regression coefficients. The local regions, where the spectral vectors are low-rank, are estimated by segmenting the HR-MSI. The formulated convex optimization is solved with SALSA. Experiments provide evidence that LRSR is competitive with respect to the state-of-the-art methods.Keywords
This publication has 13 references indexed in Scilit:
- Hyperspectral Image Super-Resolution via Non-Negative Structured Sparse RepresentationIEEE Transactions on Image Processing, 2016
- Hyperspectral Super-Resolution by Coupled Spectral Unmixing2015
- Hyperspectral Super-Resolution of Locally Low Rank Images From Complementary Multisource DataIEEE Transactions on Image Processing, 2015
- Hyperspectral and Multispectral Image Fusion Based on a Sparse RepresentationIEEE Transactions on Geoscience and Remote Sensing, 2015
- A Convex Formulation for Hyperspectral Image Superresolution via Subspace-Based RegularizationIEEE Transactions on Geoscience and Remote Sensing, 2014
- Hyperspectral Remote Sensing Data Analysis and Future ChallengesIEEE Geoscience and Remote Sensing Magazine, 2013
- Coupled Nonnegative Matrix Factorization Unmixing for Hyperspectral and Multispectral Data FusionIEEE Transactions on Geoscience and Remote Sensing, 2011
- An Augmented Lagrangian Approach to the Constrained Optimization Formulation of Imaging Inverse ProblemsIEEE Transactions on Image Processing, 2010
- Exploiting Spectral and Spatial Information in Hyperspectral Urban Data With High ResolutionIEEE Geoscience and Remote Sensing Letters, 2004
- A universal image quality indexIEEE Signal Processing Letters, 2002