Unsupervised Change Detection in Satellite Images With Generative Adversarial Network

Detecting changed regions in paired satellite images plays a key role in many remote sensing applications. The evolution of recent techniques could provide satellite images with a very high spatial resolution (VHR) but made it challenging to apply image coregistration, and many change detection methods are dependent on its accuracy. Two images of the same scene taken at different times or from different angles would introduce unregistered objects and the existence of both unregistered areas and actual changed areas would lower the performance of many change detection algorithms in unsupervised conditions. To alleviate the effect of unregistered objects in the paired images, we propose a novel change detection framework utilizing a special neural network architecture--Generative Adversarial Network (GAN) to generate many better coregistered images. In this article, we show that the GAN model can be trained upon a pair of images by using the proposed expanding strategy to create a training set and optimizing designed objective functions. The optimized GAN model would produce better coregistered images where changes can be easily spotted and then the change map can be presented through a comparison strategy using these generated images explicitly. Compared to other deep learning-based methods, our method is less sensitive to the problem of unregistered images and makes most of the deep learning structure. Experimental results on synthetic images and real data with many different scenes could demonstrate the effectiveness of the proposed approach.