Article (Scientific journals)
PlanetScope Radiometric Normalization and Sentinel-2 Super-Resolution (2.5 m): A Straightforward Spectral-Spatial Fusion of Multi-Satellite Multi-Sensor Images Using Residual Convolutional Neural Networks
Latte, Nicolas; Lejeune, Philippe
2020In Remote Sensing, 12
Peer Reviewed verified by ORBi
 

Files


Full Text
Latte and Lejeune 2020 PS radiometric normalization and S2 super-resolution.pdf
Publisher postprint (5.07 MB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
multi-sensor image fusion; image super-resolution; image pansharpening; CubeSat—Dove; radiometric correction; deep learning
Abstract :
[en] Sentinel-2 (S2) imagery is used in many research areas and for diverse applications. Its spectral resolution and quality are high but its spatial resolutions, of at most 10 m, is not sufficient for fine scale analysis. A novel method was thus proposed to super-resolve S2 imagery to 2.5 m. For a given S2 tile, the 10 S2 bands (four at 10 m and six at 20 m) were fused with additional images acquired at higher spatial resolution by the PlanetScope (PS) constellation. The radiometric inconsistencies between PS microsatellites were normalized. Radiometric normalization and super-resolution were achieved simultaneously using state-of–the-art super-resolution residual convolutional neural networks adapted to the particularities of S2 and PS imageries (including masks of clouds and shadows). The method is described in detail, from image selection and downloading to neural network architecture, training, and prediction. The quality was thoroughly assessed visually (photointerpretation) and quantitatively, confirming that the proposed method is highly spatially and spectrally accurate. The method is also robust and can be applied to S2 images acquired worldwide at any date.
Research center :
SPW
Disciplines :
Engineering, computing & technology: Multidisciplinary, general & others
Author, co-author :
Latte, Nicolas ;  Université de Liège - ULiège > Département GxABT > Gestion des ressources forestières et des milieux naturels
Lejeune, Philippe ;  Université de Liège - ULiège > Département GxABT > Gestion des ressources forestières et des milieux naturels
Language :
English
Title :
PlanetScope Radiometric Normalization and Sentinel-2 Super-Resolution (2.5 m): A Straightforward Spectral-Spatial Fusion of Multi-Satellite Multi-Sensor Images Using Residual Convolutional Neural Networks
Publication date :
23 July 2020
Journal title :
Remote Sensing
eISSN :
2072-4292
Publisher :
Multidisciplinary Digital Publishing Institute (MDPI), Basel, Switzerland
Volume :
12
Peer reviewed :
Peer Reviewed verified by ORBi
Funders :
CARTOFOR
Available on ORBi :
since 24 July 2020

Statistics


Number of views
129 (34 by ULiège)
Number of downloads
309 (17 by ULiège)

Scopus citations®
 
31
Scopus citations®
without self-citations
29
OpenCitations
 
16

Bibliography


Similar publications



Contact ORBi