Reduced-Complexity Multirate Remote Sensing Data Compression With Neural Networks

doi:10.1109/LGRS.2023.3325477

Reduced-Complexity Multirate Remote Sensing Data Compression With Neural Networks

2023-01-01

2

OA

AI

S

Sebastià Mijares i Verdú *

DOI：10.1109/LGRS.2023.3325477

Original

Original request for help

Save

Abstract

En 中文

One of the main limitations to the adoption of deep learning for image compression is the need to train multiple models to compress at multiple rates. In the case of onboard remote sensing data compression, another limitation is the computational cost of the neural networks. Addressing both limitations, this letter presents a new reduced-complexity architecture for multirate compression of remote sensing images. The proposed architecture enables compressing at a precise user-selected rate while keeping a competitive performance in lossy compression on different sets of remote sensing data. The proposed approach is amenable for onboard deployment.

Keywords:

Image coding

Bit rate

Computer architecture

Remote sensing

Modulation

Transform coding

Complexity theory

Data compression

deep learning

lossy compression

multirate

remote sensing

Reduced-Complexity Multirate Remote Sensing Data Compression With Neural Networks

Abstract

Journal

Organization