Unsupervised change detection in high spatial resolution remote sensing images based on a conditional random field model

In this paper, we propose a novel technique for unsupervised change detection in high spatial remote sensing images based on a conditional random field (CRF) model. The change-detection problem is formulated as a labeling issue to discriminate the changed class from the unchanged class in the difference image. CRF which employs the spatial property on both pixel's spectral data and labels have been widely used in many remote sensing applications. However, as there are a large number of model parameters to train, the CRF-based change-detection approach is time consuming and difficult to implement. The proposed method artfully uses memberships of Fuzzy C-means as unary potentials and defines pairwise potentials using a scaled squared Euclidean distance between neighboring pixels. This not only avoids training parameters but also helps improving the accuracy and the degree of automation. The experimental results obtained from three different remote sensing images demonstrate the accuracy and efficiency of our proposed method.