Title :

DeepSen3: Deep multi-scale learning model for spatial-spectral fusion of Sentinel-2 and Sentinel-3 remote sensing images

Author(s) :

Alboody, Ahed [Auteur]
Laboratoire d'Informatique Signal et Image de la Côte d'Opale [LISIC]
Puigt, Matthieu [Auteur]
Laboratoire d'Informatique Signal et Image de la Côte d'Opale [LISIC]
Roussel, Gilles [Auteur]
Laboratoire d'Informatique Signal et Image de la Côte d'Opale [LISIC]
Vantrepotte, Vincent [Auteur]
Laboratoire d’Océanologie et de Géosciences (LOG) - UMR 8187 [LOG]
Jamet, Cédric [Auteur]
Laboratoire d’Océanologie et de Géosciences (LOG) - UMR 8187 [LOG]
Tran, Trung-Kien [Auteur]
Laboratoire d’Océanologie et de Géosciences (LOG) - UMR 8187 [LOG]

Conference title :

2022 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS)

City :

Roma

Country :

Italie

Start date of the conference :

2022-09-13

Publication date :

2022-09

English keyword(s) :

Deep Learning
Residual Convolutional Neural Network (ResNet-CNN)
Multi-Scale Inception
Feature Extraction
Spatial-Spectral Image Fusion
Sentinel-2 and Sentinel-3 Remote Sensing Images
HyperSpectral Images (HSI)
Multi-Spectral Images (MSI)

HAL domain(s) :

Informatique [cs]/Traitement du signal et de l'image [eess.SP]

English abstract : [en]

Recently, deep learning methods that integrate image features gradually became a hot development trend in fusion of multispectral and hyperspectral remote sensing images, aka multi-sharpening. Fusion of a low spatial ...
Show more >Recently, deep learning methods that integrate image features gradually became a hot development trend in fusion of multispectral and hyperspectral remote sensing images, aka multi-sharpening. Fusion of a low spatial resolution hyperspectral image (LR-HSI datacube) with its corresponding high spatial resolution multispectral image (HR-MSI datacube) to reconstruct a high spatial resolution hyperspectral image (HR-HSI) has been a significant subject in recent years. Nevertheless, it is still difficult to achieve a high quality of spatial and spectral information fusion. In this paper, we propose a Deep Multi-Scale Learning Model (called DeepSen3) of spatial-spectral information fusion based on multi-scale inception residual convolutional neural network (CNN) for more efficient hyperspectral and multispectral image fusion from ESA remote sensing satellite missions (Sentinel-2 and Sentinel-3 images). The proposed DeepSen3 fusion network was applied to Sentinel-2 MSI (13 spectral bands with a spatial resolution ranging from 10, 20 to 60 m) and Sentinel-3 OLCI (21 spectral bands with a spatial resolution of 300 m) images. Extensive experiments demonstrate that the proposed DeepSen3 network achieves the best performance (both qualitatively and quantitatively) compared with recent state-of-the-art deep learning approaches.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

• Laboratoire d'Océanologie et de Géosciences (LOG) - UMR 8187

Source :

Harvested from HAL