Super-resolving multiresolution images with band-independant geometry of multispectral pixels

09/26/2016
by   Nicolas Brodu, et al.
0

A new resolution enhancement method is presented for multispectral and multi-resolution images, such as these provided by the Sentinel-2 satellites. Starting from the highest resolution bands, band-dependent information (reflectance) is separated from information that is common to all bands (geometry of scene elements). This model is then applied to unmix low-resolution bands, preserving their reflectance, while propagating band-independent information to preserve the sub-pixel details. A reference implementation is provided, with an application example for super-resolving Sentinel-2 data.

READ FULL TEXT

page 8

page 9

page 10

page 11

page 12

page 13

page 14

page 17

research
02/03/2020

Super-resolution of multispectral satellite images using convolutional neural networks

Super-resolution aims at increasing image resolution by algorithmic mean...
research
03/04/2021

Model-based image adjustment for a successful pansharpening

A new model-based image adjustment for the enhancement of multi-resoluti...
research
12/03/2019

Geodesic Folding of Tetrahedron

In this work, we show the geometric properties of a family of polyhedra ...
research
03/03/2020

Procedural band patterns

We seek to cover a parametric domain with a set of evenly spaced bands w...
research
08/08/2013

Satellite image classification methods and Landsat 5TM bands

This paper attempts to find the most accurate classification method amon...
research
05/07/2019

DeepSWIR: A Deep Learning Based Approach for the Synthesis of Short-Wave InfraRed Band using Multi-Sensor Concurrent Datasets

Convolutional Neural Network (CNN) is achieving remarkable progress in v...
research
06/25/2019

A CNN-Based Super-Resolution Technique for Active Fire Detection on Sentinel-2 Data

Remote Sensing applications can benefit from a relatively fine spatial r...

Please sign up or login with your details

Forgot password? Click here to reset