Change Detection in Multispectral Landsat Images Using Multi-Objective Evolutionary Algorithms

Abstract

In this letter, we propose a novel method for unsupervised change detection in multitemporal multispectral Landsat images using multiobjective evolutionary algorithm (MOEA). The proposed method minimizes two different objective functions using MOEA to provide tradeoff between each other. The objective functions are used for evaluating changed and unchanged regions of the difference image separately. The difference image is obtained by using the structural similarity index measure method, which provides combination of the comparisons of luminance, contrast, and structure between two images. By evolving a population of solutions in the MOEA, a set of Pareto optimal solution is estimated in a single run. To find the best solution, a Markov random field fusion approach is used. Experiments on semisynthetic and real-world data sets show the efficiency and effectiveness of the proposed method.