Full-Scale Regression Modeling of Spatial Details for Single-/Multiplatform Hypersharpening

Whenever the sharpening band is not unique, the hypersharpening paradigm extends traditional pansharpening to any <inline-formula> <tex-math notation="LaTeX">m </tex-math></inline-formula>-to-<inline-formula> <tex-math notation="LaTeX">n </t...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on geoscience and remote sensing Ročník 63; s. 1 - 16
Hlavní autoři: Arienzo, Alberto, Garzelli, Andrea, Alparone, Luciano, Vivone, Gemine
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Band spectra
Closed form solutions
Degradation
Environmental Mapping and Analysis Program (EnMAP)
hypersharpening
Matrix decomposition
multiband image fusion
Multisensor fusion
multivariate linear regression (MLR)
Optical imaging
optical remote sensing
Optical sensors
Optimization
Pansharpening
Parameters
Reviews
Sentinel-2 (S2)
Spatial data
Spatial resolution
Spectral bands
Tensors
Training
unimodal fusion
WorldView-3 (WV-3)
ISSN:0196-2892, 1558-0644
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Whenever the sharpening band is not unique, the hypersharpening paradigm extends traditional pansharpening to any <inline-formula> <tex-math notation="LaTeX">m </tex-math></inline-formula>-to-<inline-formula> <tex-math notation="LaTeX">n </tex-math></inline-formula> fusion task, by integrating spatial information from multiple sources. The <inline-formula> <tex-math notation="LaTeX">m </tex-math></inline-formula>-to-<inline-formula> <tex-math notation="LaTeX">n </tex-math></inline-formula> fusion task is recast into multiple 1-to-<inline-formula> <tex-math notation="LaTeX">n </tex-math></inline-formula> pansharpening problems by appropriately selecting or synthesizing a set of high-resolution (HR) bands to sharpen the set of low-resolution (LR) bands. The synthesis generates each of the sharpening bands as a linear combination of the available HR bands. The spectral coefficients of each synthetic band can be estimated using a multivariate linear regression (MLR) that matches the LR band to be sharpened. A different combination of the HR bands is assimilated into each LR band. Here, we propose a novel hypersharpening instance that directly combines high-pass spatial details, rather than low-pass image components. In general, fusion methods optimize their parameters at a reduced scale, assuming a scale-invariance property. Instead, we introduce an estimation strategy that allows the fusion parameters to be directly retrieved at the full spatial scale. Starting from an iterative process, we derive an asymptotic closed-form solution and establish its convergence conditions. Three case studies involving as many real datasets-Sentinel-2 (S2), Environmental Mapping and Analysis Program (EnMAP), and WorldView-3 (WV-3)-demonstrate performance improvements at reduced and full resolutions, obtained without any parametric optimization by the user, confirming the effectiveness and versatility of the proposed solution in single- and multiplatform fusion scenarios featuring diverse spatial resolutions, spectral bands, and resolution ratios.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2025.3614444