Remote Sensing Image Registration With Adjustable Threshold and Variational Mixture Transformation

This letter proposes a remote sensing (RS) image registration method based on adjustable threshold and variational mixture transformation (VMT). The main contributions of our method are: 1) an adjustable threshold strategy proposed to guarantee sufficient inlier pairs for image spatial transformation and 2) a VMT, which achieves a coarse-to-fine process, consisting of three main steps as follows: a) a rigid transformation is employed to achieve approximate correspondence; b) a guided Gaussian mixture model is proposed to better distinguish outliers; and c) a nonrigid transformation is applied to achieve an accurate registration. We test the performance of our algorithm in feature matching and RS image registration and compare it with the six state-of-the-art methods. Our method shows the best performances in most scenarios.