Riemannian geometry for compound Gaussian distributions: Application to recursive change detection - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Article Dans Une Revue Signal Processing Année : 2020

Riemannian geometry for compound Gaussian distributions: Application to recursive change detection

Résumé

A new Riemannian geometry for the zero-mean Compound Gaussian distribution with deterministic textures is proposed. In particular, the Fisher information metric (up to a factor) is obtained, along with corresponding geodesics and distance function. This new geometry is applied on a change detection problem on Multivariate Image Times Series: a recursive approach based on Riemannian optimization is developed. As shown on simulated data, it allows to reach optimal performance while being computationally more efficient.
Fichier principal
Vignette du fichier
PaperRecursiveChangeDetection.pdf (340.82 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02972691 , version 1 (20-10-2020)

Identifiants

Citer

Florent Bouchard, Ammar Mian, Jialun Zhou, Salem Said, Guillaume Ginolhac, et al.. Riemannian geometry for compound Gaussian distributions: Application to recursive change detection. Signal Processing, 2020, 176, pp.107716. ⟨10.1016/j.sigpro.2020.107716⟩. ⟨hal-02972691⟩
77 Consultations
6 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More