Precise change detection in multi-spectral remote sensing imagery using SIFT-based registration

In this paper we propose a robust method for geometric co registration, and an accurate change detection technique based on statistical method for multi-temporal high-resolution satellite imagery. Lhe proposed algorithm is as the following: scale-invariant feature transform (SIFT) is used to extract a set of correspondence points in a pair, or multiple pairs, of images that are taken at different times and under different circumstances, then Random Sample Consensus (RANSAC) is used to remove the outlier set. the resulting inliers matched points is an accurate correspondences which used to register the given images, changes in registered images are identified using statistical analysis of image differences. Finally, Markov-Gibbs Random Field (MGRF) is used to model the spatial-contextual information contained in the resulting change mask. Experiments with generated synthetic multiband images, and LANDSAT5 Images, approved the accuracy the proposed algorithm.