Spatial regularization for nonlinear unmixing of hyperspectral data with vector-valued kernel functions

Rita Ammanouil (1) , André Ferrari (1) , Cédric Richard (1) , Jean-Yves Tourneret (2, 3)

1 LAGRANGE - Joseph Louis LAGRANGE
2 IRIT-MINDS - CoMputational imagINg anD viSion
3 Toulouse INP - Institut National Polytechnique (Toulouse)

This communication introduces a new framework for incorporating spatial regularization into a nonlinear unmixing procedure dedicated to hyperspectral data. The proposed model promotes smooth spatial variations of the nonlinear component in the mixing model. The spatial regularizer and the nonlinear contributions are jointly modeled by a vector-valued function that lies in a reproducing kernel Hilbert space (RKHS). The unmixing problem is strictly convex and reduces to a quadratic programming (QP) problem. Simulations on synthetic data illustrate the effectiveness of the proposed approach.

Mots clés: Hyperspectral images; Nonlinear unmixing; Spatial regularization; Vector-valued RKHS

Domaines: Synthèse d'image et réalité virtuelle [cs.GR]; Traitement du signal et de l'image [eess.SP]; Traitement des images [eess.IV]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Intelligence artificielle [cs.AI]

Rita Ammanouil, André Ferrari, Cédric Richard, Jean-Yves Tourneret. Spatial regularization for nonlinear unmixing of hyperspectral data with vector-valued kernel functions. IEEE Workshop on statistical signal processing (SSP 2016), Aug 2016, Palma de Mallorca, Spain. pp. 1-5. ⟨hal-01466645⟩