Automatic binary and ternary change detection in SAR images based on evolutionary multiobjective optimization

Abstract

Listen

Translate article

In most of the previous works, changed and unchanged regions are detected by analyzing the changes of backscattering coefficients for SAR images, which is termed as binary change detection. In fact, due to the increase and decrease of backscattering coefficients, the changed regions can be further analyzed as two kinds of changes, which is termed as ternary change detection. In this paper, a change detection method based on evolutionary multiobjective optimization is proposed to automatically perform binary and ternary change detection of multitemporal SAR images. First, the log-likelihood function of the Gaussian mixture model and the Bhattacharyya distance are designed as two objectives, respectively. In particular, a novel measurement method based on Bhattacharyya distance is designed for the ternary change detection task. Not only the separability between each two classes is maximized, but also the Bhattacharyya distance between two changed classes and unchanged class is kept closer to obtain a more balanced classification performance. Then a multiobjective optimization method based on non-dominated sorting is used to optimize these two objectives simultaneously. In the proposed approach, chromosome ranking and perturbation probability selection operators are designed to make high-quality solutions with a high probability of being exploited and improve the performance of the algorithm. In addition, a one-step local search strategy based on the expectation–maximization method is integrated into the proposed algorithm to accelerate the convergence. Experimental results on simulated and real-world datasets demonstrate the effectiveness and robustness of the proposed algorithm.