Change Detection in Satellite Images Using a Genetic Algorithm Approach

In this letter, we propose a novel method for unsupervised change detection in multitemporal satellite images by minimizing a cost function using a genetic algorithm (GA). The difference image computed from the multitemporal satellite images is partitioned into two distinct regions, namely, "changed" and "unchanged," according to the binary change detection mask realization from the GA. For each region, the mean square error (MSE) between its difference image values and the average of its difference image values is calculated. The weighted sum of the MSE of the changed and unchanged regions is used as a cost value for the corresponding change detection mask realization. The GA is employed to find the final change detection mask with the minimum cost by evolving the initial realization of the binary change detection mask through generations. The proposed method is able to produce the change detection result on the difference image without a priori assumptions. Change detection results are shown on multitemporal Advanced Synthetic Aperture Radar images acquired by the ESA/Envisat satellite and on multitemporal optical images acquired by the Landsat multispectral scanner. The comparisons with the state-of-the-art change detection methods are provided.