Super-Resolution of Sentinel-2 Images: Learning a Globally Applicable Deep Neural Network

03/12/2018
by   Charis Lanaras, et al.
0

The Sentinel-2 satellite mission delivers multi-spectral imagery with 13 spectral bands, acquired at three different spatial resolutions. The aim of this research is to super-resolve the lower-resolution (20 m and 60 m Ground Sampling Distance - GSD) bands to 10 m GSD, so as to obtain a complete data cube at the maximal sensor resolution. We employ a state-of-the-art convolutional neural network (CNN) to perform end-to-end upsampling, which is trained with data at lower resolution, i.e., from 40->20 m, respectively 360->60 m GSD. In this way, one has access to a virtually infinite amount of training data, by downsampling real Sentinel-2 images. We use data sampled globally over a wide range of geographical locations, to obtain a network that generalises across different climate zones and land-cover types, and can super-resolve arbitrary Sentinel-2 images without the need of retraining. In quantitative evaluations (at lower scale, where ground truth is available), our network outperforms the best competing approach by almost 50 better preserving the spectral characteristics. It also delivers visually convincing results at the full 10 m GSD.

READ FULL TEXT

page 2

page 3

page 7

page 11

page 12

page 13

page 14

research
02/07/2019

Advances on CNN-based super-resolution of Sentinel-2 images

Thanks to their temporal-spatial coverage and free access, Sentinel-2 im...
research
01/26/2023

Multitemporal and multispectral data fusion for super-resolution of Sentinel-2 images

Multispectral Sentinel-2 images are a valuable source of Earth observati...
research
09/05/2019

Super-resolved Chromatic Mapping of Snapshot Mosaic Image Sensors via a Texture Sensitive Residual Network

This paper introduces a novel method to simultaneously super-resolve and...
research
10/16/2020

A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery

Combining satellite imagery with machine learning (SIML) has the potenti...
research
11/09/2020

Fast Fourier Intrinsic Network

We address the problem of decomposing an image into albedo and shading. ...
research
06/01/2019

Super-resolution of Time-series Labels for Bootstrapped Event Detection

Solving real-world problems, particularly with deep learning, relies on ...

Please sign up or login with your details

Forgot password? Click here to reset