Automatic remote sensing image registration based on SIFT descriptor and image classification

The Scale Invariant Feature Transform (SIFT) has been widely used in remote sensing image registration. However, there are many false matches when it is adopted to align images of different sensors. In this paper, a new method based on the combination of image classification and SIFT descriptor is proposed to improve the performance of registration. Experiment results support the potential of the proposed approach in remote sensing image registration.