A Novel SSDA-Based Block Matching Algorithm for Image Stabilization

摘要

In this paper, a novel SSDA-based block matching algorithm for image stabilization is proposed. Block matching is a general and most frequently used image stabilization method with high stability and quality. And the Sequential Similarity Detection Algorithm (SSDA) is an efficient tool in the determination of local similarity between two data sets. Therefore we put forward an improved SSDA to accelerate the processing speed. Besides, Sparsity Strategy and Weighted MAD-based Voting Theory are also introduced. Experimental results demonstrate that the proposed method outperforms previous algorithms in terms of rapidity and accuracy.