Improved Chaotic Particle Swarm Optimization with Variance Based Novel Objective Function for Pansharpening in Remote Sensing.

This article focuses on an improved pansharpening method for remote sensing image fusion that integrates a Chaotic Particle Swarm Optimization (CPSO) framework with a novel variance-based objective function and fusion rule. The approach employs a chaotic logistic map to initialize particle positions in PSO, enhancing convergence and diversity, and introduces a modified ERGAS (Erreur Relative Globale Adimensionnelle de Synthèse) index based on local variance to better preserve spatial details. A variance-based Max fusion rule is applied to RGB and NIR bands to improve edge and spectral fidelity. Experimental results on seven datasets from QuickBird and Landsat-7 satellites demonstrate that this method outperforms existing techniques across multiple image quality metrics, offering a computationally efficient, unsupervised fusion strategy suitable for remote sensing applications.