Remote sensing image matching by integrating affine invariant feature extraction and RANSAC

[Display omitted] ► We propose an automatic optimization for affine invariant feature matching. ► We design an experiment to compare optimization with un-optimization. ► The optimization technology can get higher correctness of image matching. A new technical framework for remote sensing image matching by integrating affine invariant feature extraction and RANSAC is presented. The novelty of this framework is an automatic optimization strategy for affine invariant feature matching based on RANSAC. An automatic way to determine the distance threshold of RANSAC is proposed, which is a key problem to implement this RANSAC-based automatic optimization. Since affine invariant feature matching technology has been successfully applied to remote sensing image matching, we design an experiment to compare the proposed framework (with optimization) with the standard affine invariant feature matching (without optimization). By using three pairs with different types of imagery, the experimental results indicate that the proposed framework can always get higher correctness of image matching in automatic way, compared to the standard affine invariant feature matching technology.