Mismatch Removal for Remote Sensing Images Based on Non-Rigid Transformation and Local Geometrical Constraint

Feature matching, which refers to the establishment of accurate correspondence between two sets of feature points, plays an important role in the field of computer vision and remote sensing. Focusing on the characteristics of remote sensing images, this paper proposes a new algorithm for robust feature matching based on non-rigid transformation, which formulates the feature matching problem as a probabilistic model. Specifically, we first utilize the scale-invariant feature transform to establish the initial feature correspondences between an image pair, and the thin-plate spline is adopted for non-rigid transformation modeling, where a local geometric constraint is introduced to maintain local structures of neighboring feature points after the transformation. Under the Bayesian framework, we seek a maximum a posteriori solution of our model by using the expectation-maximization algorithm. In addition, without sacrificing the matching accuracy, we provide a fast implementation to reduce the computational complexity of the algorithm based on sparse approximation. We verify the performance of our method on a large number of remote sensing images, and the qualitative and quantitative results reveal its superiority over the state-of-the-art.