Reduced-Complexity Multirate Remote Sensing Data Compression With Neural Networks

Sebastià Mijares Verdú, Marie Chabert, Thomas Oberlin, Joan Serra Sagrista

Research output: Contribution to journalArticleResearchpeer-review

1 Downloads (Pure)

Abstract

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.
Original languageEnglish
Article number6011705
Number of pages5
JournalIEEE Geoscience and Remote Sensing Letters
Volume20
DOIs
Publication statusPublished - 20 Oct 2023

Keywords

  • Data compression
  • Lossy compression
  • Deep learning
  • Multirate
  • Remote sensing

Fingerprint

Dive into the research topics of 'Reduced-Complexity Multirate Remote Sensing Data Compression With Neural Networks'. Together they form a unique fingerprint.

Cite this