CSSNET: A Learning Algorithm for the Segmentation of Compressed Hyperspectral Images - LAAS - Laboratoire d'Analyse et d'Architecture des Systèmes Access content directly
Conference Papers Year : 2022

CSSNET: A Learning Algorithm for the Segmentation of Compressed Hyperspectral Images

Maud Biquard
  • Function : Author
  • PersonId : 1109804
Simon Lacroix
Antoine Rouxel
  • Function : Author
  • PersonId : 1109805
Antoine Monmayrant
Henri Camon

Abstract

The paper presents a semantic segmentation method which is directly applicable to compressed hyperspectral images acquired with a dual-disperser CASSI instrument. It introduses an algorithm based on a shallow neural network that exploits the spectral filtering performed by the optical system and the compressed hyperspectral images measured by the detector. Encouraging results that exploit 50 to 100 less data than the whole hyperspectral datacube on PaviaU and IndianPines datasets are presented.
Fichier principal
Vignette du fichier
whispers2022.pdf (1.39 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03746594 , version 1 (05-08-2022)

Identifiers

Cite

Maud Biquard, Simon Lacroix, Antoine Rouxel, Hervé Carfantan, Antoine Monmayrant, et al.. CSSNET: A Learning Algorithm for the Segmentation of Compressed Hyperspectral Images. Workshop on Hyperspectral Images and Signal Processing: Evolution in Remote Sensing (WHISPERS 2022), Sep 2022, Rome, Italy. ⟨10.1109/WHISPERS56178.2022.9955065⟩. ⟨hal-03746594⟩
92 View
47 Download

Altmetric

Share

Gmail Facebook X LinkedIn More