Final published version
Licence: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Unpaired spatio-temporal fusion of image patches (USTFIP) from cloud covered images
AU - Goyena, H.
AU - Pérez-Goya, U.
AU - Montesino-SanMartin, M.
AU - Militino, A.F.
AU - Wang, Q.
AU - Atkinson, P.M.
AU - Ugarte, M.D.
N1 - Export Date: 3 August 2023
PY - 2023/9/1
Y1 - 2023/9/1
N2 - Spatio-temporal image fusion aims to increase the frequency and resolution of multispectral satellite sensor images in a cost-effective manner. However, practical constraints on input data requirements and computational cost prevent a wider adoption of these methods in real case-studies. We propose an ensemble of strategies to eliminate the need for cloud-free matching pairs of satellite sensor images. The new methodology called Unpaired Spatio-Temporal Fusion of Image Patches (USTFIP) is tested in situations where classical requirements are progressively difficult to meet. Overall, the study shows that USTFIP reduces the root mean square error by 2-to-13% relative to the state-of-the-art Fit-FC fusion method, due to an efficient use of the available information. Implementation of USTFIP through parallel computing saves up to 40% of the computational time required for Fit-FC.
AB - Spatio-temporal image fusion aims to increase the frequency and resolution of multispectral satellite sensor images in a cost-effective manner. However, practical constraints on input data requirements and computational cost prevent a wider adoption of these methods in real case-studies. We propose an ensemble of strategies to eliminate the need for cloud-free matching pairs of satellite sensor images. The new methodology called Unpaired Spatio-Temporal Fusion of Image Patches (USTFIP) is tested in situations where classical requirements are progressively difficult to meet. Overall, the study shows that USTFIP reduces the root mean square error by 2-to-13% relative to the state-of-the-art Fit-FC fusion method, due to an efficient use of the available information. Implementation of USTFIP through parallel computing saves up to 40% of the computational time required for Fit-FC.
KW - Clouds
KW - Fit-FC
KW - Parallel computing
KW - Satellite imagery
KW - Spatio-temporal image fusion
U2 - 10.1016/j.rse.2023.113709
DO - 10.1016/j.rse.2023.113709
M3 - Journal article
VL - 295
JO - Remote Sensing of Environment
JF - Remote Sensing of Environment
SN - 0034-4257
M1 - 113709
ER -