Titre :

DNGAE: Deep Neighborhood Graph Autoencoder for Robust Blind Hyperspectral Unmixing

Auteur(s) :

Hanachi, Refka [Auteur]
Laboratoire de recherche en Génie Logiciel, Applications distribuées, Systèmes décisionnels et Imagerie intelligente [Manouba] [RIADI]
Sellami, Akrem [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Farah, Imed Riadh [Auteur]
Département lmage et Traitement Information [IMT Atlantique - ITI]
Laboratoire de recherche en Génie Logiciel, Applications distribuées, Systèmes décisionnels et Imagerie intelligente [Manouba] [RIADI]
Dalla Mura, Mauro [Auteur]
GIPSA - Signal Images Physique [GIPSA-SIGMAPHY]

Titre de la manifestation scientifique :

ICCCI 2023- 15th International Conference on Computational Collective Intelligence (ICCCI)

Ville :

Budapest

Pays :

Hongrie

Date de début de la manifestation scientifique :

2023-09-27

Titre de l’ouvrage :

International Conference on Computational Collective Intelligence

Titre de la revue :

Lecture Notes in Computer Science

Éditeur :

Springer Nature Switzerland

Lieu de publication :

Cham

Date de publication :

2023-09-13

Mot(s)-clé(s) en anglais :

Spectral unmixing
Neighborhood graph
Representation learning
Graph Autoencoder

Discipline(s) HAL :

Informatique [cs]/Traitement du signal et de l'image [eess.SP]
Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]

Résumé en anglais : [en]

Recently, Deep Learning (DL)-based unmixing techniques have gained popularity owing to the robust learning of Deep Neural Networks (DNNs). In particular, the Autoencoder (AE) model, as a baseline network for unmixing, ...
Lire la suite >Recently, Deep Learning (DL)-based unmixing techniques have gained popularity owing to the robust learning of Deep Neural Networks (DNNs). In particular, the Autoencoder (AE) model, as a baseline network for unmixing, performs well in Hyperspectral Unmixing (HU) by automatically learning a new representation and recovering original data. However, patch-wise AE based architecture, which incorporates both spectral and spatial information through convolutional filters may blur the abundance maps due to the fixed kernel shape of the used window size. To cope with the above issue, we propose in this paper a novel methodology based on graph DL called DNGAE. Unlike the pixel-wise or patch-wise Convolutional AE (CAE), our proposed method incorporates the complementary spatial information based on graph spectral similarity. A neighborhood graph based on band correlations is firstly constructed. Then, our method attempts to aggregate similar spectra from the neighboring pixels of a target pixel. Consequently, this leads to better quality of both extracted endmembers and abundances. Extensive experiments performed on two real HSI benchmarks confirm the effectiveness of our proposed method compared to other DL models.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL