Hyperspectral and Multispectral Image Fusion Based on a Sparse Representation

By Qi Wei, José M. Bioucas-Dias, Nicolas Dobigeon, Jean-Yves Tourneret. IEEE Transactions on Geoscience and Remote Sensing, 2014

568 citations recorded by the source corpus.

This paper presents a variational-based approach for fusing hyperspectral and multispectral images. The fusion problem is formulated as an inverse problem whose solution is the target image assumed to live in a lower dimensional subspace. A sparse regularization term is carefully designed, relying on a decomposition of the scene on a set of dictionaries. The dictionary atoms and the supports of the corresponding active coding coefficients are learned from the observed images. Then, conditionally on these dictionaries and supports, the fusion problem is solved via alternating optimization with respect to the target image (using the alternating direction method of multipliers) and the coding coefficients. Simulation results demonstrate the efficiency of the proposed algorithm when compared with state-of-the-art fusion methods.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/046da8beaadd5ab6ad612f970224621b2fb93e5e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Hyperspectral Image Super-Resolution via Non-Negative Structured Sparse Representation (2016, methodology): “It can be seen that the proposed algorithm runs much faster than the BSR method [37] and the G-SOMP+ method [26].”
Hyperspectral and Multispectral Data Fusion: A comparative review of the recent literature (2017, methodology): “• A Gaussian filter with an FWHM at GSD was used for all the methods that require PSF except HySure.”
Fast Fusion of Multi-Band Images Based on Solving a Sylvester Equation (2015, methodology): “In [20], the MAP estimator associated with this model was reached using an optimizatio n algorithm that consists of an ADMM step embedded in a BCD method (ADMM-BCD).”
Fusing Hyperspectral and Multispectral Images via Coupled Sparse Tensor Factorization (2018, methodology): “Both the LR-HSI and HRMSI can be modeled as downsampled versions of the HR-HSI [26], [28], i.”
Pixel-level image fusion: A survey of the state of the art (2017, methodology): “(In this figure, the fusion of MS with PAN and hyperspectral images are achieved using the matting model based method[80] and the sparse representation based method [125], respectively.”
Hyperspectral Pansharpening: A Review (2015, methodology): “U and A has been introduced in [36] (where details on the learning of D̄, Ω̄ and H can be found).”
Hyperspectral Image Super-Resolution via Non-local Sparse Tensor Factorization (2017, methodology): “By imposing priors on the distribution of the image intensities, Bayesian approaches [33, 3] apply MAP inference to regularize the fusion problem.”
A review of remote sensing image fusion methods (2016, methodology): “AC CE PT ED M AN US CR IP T A method for fusing of HS and MS image based on a sparse representation has been introduced in [6].”
Multisource and Multitemporal Data Fusion in Remote Sensing: A Comprehensive Review of the State of the Art (2019, background): “For each category, from left to right, the circles correspond to [42]–[50] for CS; [51]–[57] for MRA; [27], [31], and [58]–[63] for geostatistical; [64]–[69] for subspace; and [70]–[72] for sparse.”
Deep Hyperspectral Image Sharpening (2018, methodology): “HSI sharpening algorithms can be roughly categorized into two types: matrix factorization-based methods [1], [35]–[41] and tensor factorization methods [42].”
Learning a Low Tensor-Train Rank Representation for Hyperspectral Image Super-Resolution (2019, methodology): “[32] assume that the HSIs lie in a low-dimensional subspace and use the spatial dictionaries learned from the HRMSI to promote the spatial similarities.”