Change Detection in Semantic Level for SAR Images

Considering that the traditional change detection algorithms only focus on extracting the change area but ignore the change content identification, a novel change detection framework for synthetic aperture radar (SAR) images is proposed. The framework integrates the merits of unsupervised and supervised learning to detect changes in semantic level. First, the residual convolutional auto-encoder (RCAE) is designed to convert SAR image slices to the histogram representation. Then, we calculate the difference vectors and extract the change area by their norms. Finally, we classify the difference vectors of change region and identify the content of change. Experimental results indicate that the proposed method achieves significantly performance improvement over existing algorithms.