A Novel SAR Image Registration Method Based On Feature Extraction And Area Optimization

Synthetic Aperture Radar(SAR)image registration method is the fundamental technology for high-level SAR image applications like change detection and disaster monitor.It plays an important role in these fields.Optical image registration methods can be divided into two classes: feature-based registration methods and area-based methods.Feature-based methods extract features from the pre-registered images and then compute the transformation matrix.Area-based methods transform the image registration into an optimization problem.These methods have succeeded in optical image registration.However,applying these methods for SAR image registration would not work.Because of the multiple noises academically called “speckles”,feature-based methods would generate many mis-matching feature pairs that lead to errors.And because of the size of SAR image and speckles,area-based methods always converge to local optima and are computationally expensively.This paper proposes a novel SAR image registration method.First,the traditional area-based optimization model is reconstructed and decomposed into three key but uncertain factors: initialization,slice set and regularization.Next,structural features are extracted by scale invariant feature transform(SIFT)in dual-resolution space(SIFT-DRS),a novel SIFT-Like method dedicated to FAO.Then,the three key factors are determined based on these features.Finally,solving the factor-determined optimization model can get the registration result.A series of experiments demonstrate that the proposed method can register multi-temporal SAR images accurately and efficiently.