Satellite Image Compression and Denoising With Neural Networks

Earth observation through satellite images is crucial to help economic activities as well as to monitor the impact of human activities on ecosystems. Current satellite systems are subjected to strong computational complexity constraints. Thus, image compression is performed onboard with specifically...

Full description

Saved in:
Bibliographic Details
Published in:IEEE geoscience and remote sensing letters 2022-01, Vol.19, p.1-5
Main Authors: Alves de Oliveira, Vinicius, Chabert, Marie, Oberlin, Thomas, Poulliat, Charly, Bruno, Mickael, Latry, Christophe, Carlavan, Mikael, Henrot, Simon, Falzon, Frederic, Camarero, Roberto
Format: Article
Language:English
Subjects:
Algorithms
Compression
Compressive strength
Computer applications
Computer architecture
Computer Science
Data compression
Earth observations (from space)
Economic activities
Engineering Sciences
Human influences
Image coding
Image compression
image denoising
Imaging
Impact analysis
Mathematics
Neural networks
Noise reduction
Onboard
Satellite imagery
Satellite observation
Satellites
Spaceborne remote sensing
Statistics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Earth observation through satellite images is crucial to help economic activities as well as to monitor the impact of human activities on ecosystems. Current satellite systems are subjected to strong computational complexity constraints. Thus, image compression is performed onboard with specifically tailored algorithms while image denoising is performed on the ground. In this letter, we intend to address satellite image compression and denoising with neural networks. The first proposed approach uses a single neural architecture for joint onboard compression and denoising. The second proposed approach sequentially uses a first neural architecture for onboard compression and a second one for on ground denoising. For both approaches, the onboard architectures are lightened as much as possible, following the procedure proposed by Alves de Oliveira et al. (2021). The two approaches are shown to outperform the current satellite imaging system and their respective pros and cons are discussed.
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2022.3145992