A multi-objective component-substitution-based pansharpening

Abstract

This paper proposes a multi-objective approach to improving the component substitution (CS) based pansharpening method by obtaining the adaptive weights. The non-dominated sorting genetic algorithm II (NSGA-II) is employed to simultaneously optimize two objective functions. The inverse of the Correlation Coefficient (CC) and a weighted sum of the Erreur Relative Globale Adimensionnelle de Synthese (ERGAS) in the spectral and spatial domains are used as the objective functions. The use of a multi-objective approach in the CS technique allows optimizing the fused image in terms of both spatial and spectral resolutions. Simulation results show that the proposed method outperforms popular CS-based fusion methods.