Spatial–Spectral Interaction Super-Resolution CNN–Mamba Network for Fusion of Satellite Hyperspectral and Multispectral Image

The tradeoff between spatial and spectral resolution in sensor design is inevitable, and spatial–spectral fusion aims to use low spatial resolution hyperspectral image (HSI) and high spatial resolution (HR) multispectral image (MSI) obtained at the same time and in the same area to recons...

Full description

Saved in:
Bibliographic Details
Main Authors: Guangwei Zhao, Haitao Wu, Dexiang Luo, Xu Ou, Yu Zhang
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10695805/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850209985375502336
author Guangwei Zhao
Haitao Wu
Dexiang Luo
Xu Ou
Yu Zhang
author_facet Guangwei Zhao
Haitao Wu
Dexiang Luo
Xu Ou
Yu Zhang
author_sort Guangwei Zhao
collection DOAJ
description The tradeoff between spatial and spectral resolution in sensor design is inevitable, and spatial–spectral fusion aims to use low spatial resolution hyperspectral image (HSI) and high spatial resolution (HR) multispectral image (MSI) obtained at the same time and in the same area to reconstruct HR HSI. Recently, a large number of deep-learning methods have been applied in this field and achieved success. However, these methods do not fully utilize the characteristics of data for network design, and cannot guarantee effective computational efficiency in extracting local and global features. To solve the above problems, we designed a spatial–spectral interaction super-resolution convolutional neural network (CNN)–Mamba fusion network for satellite HSI and MSI, which uses mutual guidance to improve the spatial and spectral resolution of different data, and obtains the final fused image through feature fusion. In addition, we combined Mamba with CNN to effectively explore global and local features of images. Extensive experiments have proven that our method can reconstruct fused images of high quality and is superior to current state-of-the-art fusion methods.
format Article
id doaj-art-c7ebf0078e2148758e94f94ae826de6e
institution OA Journals
issn 1939-1404
2151-1535
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-c7ebf0078e2148758e94f94ae826de6e2025-08-20T02:09:52ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352024-01-0117184891850110.1109/JSTARS.2024.346918410695805Spatial–Spectral Interaction Super-Resolution CNN–Mamba Network for Fusion of Satellite Hyperspectral and Multispectral ImageGuangwei Zhao0https://orcid.org/0009-0008-5863-9639Haitao Wu1Dexiang Luo2https://orcid.org/0009-0002-3810-4289Xu Ou3Yu Zhang4College of Computing and Artificial Intelligence, Huanghuai University, Zhumadian, ChinaCollege of Computing and Artificial Intelligence, Huanghuai University, Zhumadian, ChinaInformation Centre of Guangxi Medical University, Nanning, ChinaInformation Centre of Guangxi Medical University, Nanning, ChinaCollege of Computing and Artificial Intelligence, Huanghuai University, Zhumadian, ChinaThe tradeoff between spatial and spectral resolution in sensor design is inevitable, and spatial–spectral fusion aims to use low spatial resolution hyperspectral image (HSI) and high spatial resolution (HR) multispectral image (MSI) obtained at the same time and in the same area to reconstruct HR HSI. Recently, a large number of deep-learning methods have been applied in this field and achieved success. However, these methods do not fully utilize the characteristics of data for network design, and cannot guarantee effective computational efficiency in extracting local and global features. To solve the above problems, we designed a spatial–spectral interaction super-resolution convolutional neural network (CNN)–Mamba fusion network for satellite HSI and MSI, which uses mutual guidance to improve the spatial and spectral resolution of different data, and obtains the final fused image through feature fusion. In addition, we combined Mamba with CNN to effectively explore global and local features of images. Extensive experiments have proven that our method can reconstruct fused images of high quality and is superior to current state-of-the-art fusion methods.https://ieeexplore.ieee.org/document/10695805/Convolutional neural network (CNN)fusionhyperspectralMambamultispectral
spellingShingle Guangwei Zhao
Haitao Wu
Dexiang Luo
Xu Ou
Yu Zhang
Spatial–Spectral Interaction Super-Resolution CNN–Mamba Network for Fusion of Satellite Hyperspectral and Multispectral Image
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Convolutional neural network (CNN)
fusion
hyperspectral
Mamba
multispectral
title Spatial–Spectral Interaction Super-Resolution CNN–Mamba Network for Fusion of Satellite Hyperspectral and Multispectral Image
title_full Spatial–Spectral Interaction Super-Resolution CNN–Mamba Network for Fusion of Satellite Hyperspectral and Multispectral Image
title_fullStr Spatial–Spectral Interaction Super-Resolution CNN–Mamba Network for Fusion of Satellite Hyperspectral and Multispectral Image
title_full_unstemmed Spatial–Spectral Interaction Super-Resolution CNN–Mamba Network for Fusion of Satellite Hyperspectral and Multispectral Image
title_short Spatial–Spectral Interaction Super-Resolution CNN–Mamba Network for Fusion of Satellite Hyperspectral and Multispectral Image
title_sort spatial x2013 spectral interaction super resolution cnn x2013 mamba network for fusion of satellite hyperspectral and multispectral image
topic Convolutional neural network (CNN)
fusion
hyperspectral
Mamba
multispectral
url https://ieeexplore.ieee.org/document/10695805/
work_keys_str_mv AT guangweizhao spatialx2013spectralinteractionsuperresolutioncnnx2013mambanetworkforfusionofsatellitehyperspectralandmultispectralimage
AT haitaowu spatialx2013spectralinteractionsuperresolutioncnnx2013mambanetworkforfusionofsatellitehyperspectralandmultispectralimage
AT dexiangluo spatialx2013spectralinteractionsuperresolutioncnnx2013mambanetworkforfusionofsatellitehyperspectralandmultispectralimage
AT xuou spatialx2013spectralinteractionsuperresolutioncnnx2013mambanetworkforfusionofsatellitehyperspectralandmultispectralimage
AT yuzhang spatialx2013spectralinteractionsuperresolutioncnnx2013mambanetworkforfusionofsatellitehyperspectralandmultispectralimage