Quasi Lossless Satellite Image Compression - UFR ISTIC Informatique et électronique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Quasi Lossless Satellite Image Compression

Résumé

We describe an end-to-end trainable neural network for satellite image compression. The proposed approach builds upon an image compression scheme based on variational autoencoders with a learned hyper-prior that captures dependencies in the latent space for entropy coding. We explore this architecture in light of specificities of satellite imaging: processing constraints onboard the satellite (complexity and memory constraints) and quality needed in terms of reconstruction for the processing task on the ground. We explore data augmentation to improve the reconstruction of challenging image patterns. The proposed model outperforms the current standard of lossy image compression onboard satellite based on JPEG 2000, as well as the initial hyper-prior architecture designed for natural images.
Fichier principal
Vignette du fichier
IGARSS_2022_BACCHUS.pdf (1.01 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03807986 , version 1 (10-10-2022)
hal-03807986 , version 2 (23-05-2023)

Identifiants

Citer

Pascal Bacchus, Renaud Fraisse, Aline Roumy, Christine Guillemot. Quasi Lossless Satellite Image Compression. IGARSS 2022 - International Geoscience and Remote Sensing Symposium, Jul 2022, Kuala Lumpur, Indonesia. pp.1-4, ⟨10.1109/IGARSS46834.2022.9883135⟩. ⟨hal-03807986v2⟩
80 Consultations
117 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More