Robust Detection using M- estimators for Hyperspectral Imaging

Joana Frontera-Pons; Mélanie Mahot; Jean-Philippe Ovarlez; Frédéric Pascal; Jocelyn Chanussot

Robust Detection using M- estimators for Hyperspectral Imaging

Joana Frontera-Pons ¹ Mélanie Mahot ¹ Jean-Philippe Ovarlez ^{1, 2} Frédéric Pascal ¹ Jocelyn Chanussot ³

1 SONDRA - Sondra, CentraleSupélec, Université Paris-Saclay

2 ONERA - The French Aerospace Lab [Palaiseau]

3 GIPSA-SIGMAPHY - SIGMAPHY

GIPSA-DIS - Département Images et Signal

Abstract : Hyperspectral data have been proved not to be multivariate normal but long tailed distributed. In order to take into account these features, the family of elliptical contoured distributions is proposed to describe noise statistical behavior. Although non-Gaussian models are assumed for background modeling and detectors design, the parameters estimation is still performed using classical Gaussian based estimators; as for the covariance matrix, generally determined according to the SCM approach. We discuss here the class of M-estimators as a robust alternative for background statistical characterization and highlight their outcome when used in an adaptive GLRT-LQ detector.

Document type :

Conference papers

Domain :

Engineering Sciences [physics] / Signal and Image processing

Computer Science [cs] / Signal and Image Processing

Complete list of metadatas

https://hal-supelec.archives-ouvertes.fr/hal-00780777
Contributor : Anne-Hélène Picot <>
Submitted on : Thursday, January 24, 2013 - 5:54:29 PM
Last modification on : Friday, June 21, 2019 - 11:18:04 AM

Robust Detection using M- estimators for Hyperspectral Imaging

Identifiers

Collections

Citation

Export

Metrics

476

Contact

Robust Detection using M- estimators for Hyperspectral Imaging

Identifiers

Collections

Citation

Export

Share

Metrics

476

Contact