A Robust Matching Method for Optical and SAR Images Based on Coarse-to-Fine Mechanism

Although image matching techniques have been developed in the last decades, automatic optical-synthetic aperture radar (SAR) image matching is still a challenging task due to significant nonlinear intensity differences between such images. In this paper, a new method of coarse-to-fine heterogeneous image matching based on contour features is proposed. After images preprocessing, a Canny operator is used to extract open-loop contour features, and the angle feature of local feature points is used to complete coarse matching. Finally, constructing contour tree descriptors of coarse matching pairs, and calculating the contour distance is proposed to obtain the fine matching result. The experimental results show the effectiveness and robustness of this method.