Reduced-Complexity Multirate Remote Sensing Data Compression With Neural Networks - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Geoscience and Remote Sensing Letters Année : 2023

Reduced-Complexity Multirate Remote Sensing Data Compression With Neural Networks

Résumé

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.
Fichier principal
Vignette du fichier
Reduced-Complexity_Multirate_Remote_Sensing_Data_Compression_With_Neural_Networks.pdf (4.22 Mo) Télécharger le fichier
Origine : Publication financée par une institution

Dates et versions

hal-04327715 , version 1 (06-12-2023)

Licence

Paternité

Identifiants

Citer

Sebastià Mijares I Verdú, Marie Chabert, Thomas Oberlin, Joan Serra-Sagristà. Reduced-Complexity Multirate Remote Sensing Data Compression With Neural Networks. IEEE Geoscience and Remote Sensing Letters, 2023, 20, pp.6011705. ⟨10.1109/lgrs.2023.3325477⟩. ⟨hal-04327715⟩
27 Consultations
12 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More