Abstract:In order to improve the stability and reliability of Synthetic Aperture Radar(SAR) images matching, a new scene matching algorithm for SAR images based on Scale Invariant Feature Transform (SIFT) features was proposed. Numerous experiments were conducted for homologous and non-homologous SAR images under various conditions, and the preliminary matching conclusions were obtained. The experimental results demonstrates that the proposed approach is stable，reliable，efficient and robust for the data used in the paper.