Hyperspectral Super-Resolution: A Coupled Tensor Factorization Approach

DOI10.1109/TSP.2018.2876362MaRDI QIDQ4622542zbMATH OpenOpenAlexWikidataFDO

Authors Charilaos I. Kanatsoulis, Xiao Fu, Nicholas D. Sidiropoulos, Wing-Kin Ma

Publication date 12 February 2019

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1804.05307

Mathematics Subject Classification ID

Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Abstract: Hyperspectral super-resolution refers to the problem of fusing a hyperspectral image (HSI) and a multispectral image (MSI) to produce a super-resolution image (SRI) that has fine spatial and spectral resolution. State-of-the-art methods approach the problem via low-rank matrix approximations to the matricized HSI and MSI. These methods are effective to some extent, but a number of challenges remain. First, HSIs and MSIs are naturally third-order tensors (data "cubes") and thus matricization is prone to loss of structural information--which could degrade performance. Second, it is unclear whether or not these low-rank matrix-based fusion strategies can guarantee identifiability or exact recovery of the SRI. However, identifiability plays a pivotal role in estimation problems and usually has a significant impact on performance in practice. Third, the majority of the existing methods assume that there are known (or easily estimated) degradation operators applied to the SRI to form the corresponding HSI and MSI--which is hardly the case in practice. In this work, we propose to tackle the super-resolution problem from a tensor perspective. Specifically, we utilize the multidimensional structure of the HSI and MSI to propose a coupled tensor factorization framework that can effectively overcome the aforementioned issues. The proposed approach guarantees the identifiability of the SRI under mild and realistic conditions. Furthermore, it works with little knowledge of the degradation operators, which is clearly an advantage over the existing methods. Semi-real numerical experiments are included to show the effectiveness of the proposed approach.

Cited in

(14)

• Information theory and recovery algorithms for data fusion in Earth observation
• Non-local blind hyperspectral image super-resolution via 4D sparse tensor factorization and low-rank
• Classification of hyperspectral images as tensors using nonnegative CP decomposition
• Hyperspectral Super-resolution Accounting for Spectral Variability: Coupled Tensor LL1-Based Recovery and Blind Unmixing of the Unknown Super-resolution Image
• A super-resolution framework for tensor decomposition
• Hyperspectral super-resolution via low rank tensor triple decomposition
• A random matrix approach to low-multilinear-rank tensor approximation
• Subspace-based coupled tensor decomposition for hyperspectral blind fusion
• Rethinking coupled tensor analysis for hyperspectral superresolution: recoverable modeling under endmember variability
• Hyperspectral super-resolution via tensor CP decomposition with total variation regularization
• A coarse-to-fine hybrid registration and fusion framework for hyperspectral superresolution via batch image alignment
• Blind hyperspectral and multispectral images fusion: a unified tensor fusion framework from coupled inverse problem perspective
• Hyperspectral super-resolution with inter-image variability via degradation-based low-rank and residual fusion method
• Key-frame detection and super-resolution of hyperspectral video via sparse-based cumulative tensor factorization

This page was built for publication: Hyperspectral Super-Resolution: A Coupled Tensor Factorization Approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4622542)