SAR image restoration and change detection based on game theory

In this paper, a novel unsupervised change detection algorithm based on game theory is proposed for synthetic aperture radar(SAR) images. With the introduction of Nash-game theory, we find the balance of segmentation accuracy and overall restoration performance. Restoration of images plays a denoising role due to the complex movement while obtaining a SAR image. The Segmentation procedure transfers the difference map into change map. To make the algorithm less time-consuming, we analyze the state-of-the-art methods for generating the change map and finally select the minus map as the preferred one. The experiment based on the proposed methodology proves the accuracy and robustness of our algorithm compared with several well-known change detection techniques on both noise-free and noisy satellite images. Further optimization methods are discussed in the end.