Feature Point Matching Based on Multi-Scale Local Relative Motion Consistency

Matching feature points from image pairs with significant visual changes and repetitive patterns remains a challenging problem due to the presence of mismatches in the putative corresponding point sets. In this paper, we propose a novel feature matching algorithm called Multi-scale Local Relative Motion Consistency (MLRMC) to accurately find matched feature points. The MLRMC algorithm exploits the multi-scale relative motion information between putative matches and their neighboring points to effectively remove outliers with accuracy and robustness. By clustering the relative motion, coincident relative motion among the matches is obtained. The similarity of each putative match is evaluated by considering both the consensus of relative motion and the consensus of neighborhood elements. To achieve accurate and robust feature point matching, a two-step outlier removal strategy is employed. Experimental evaluations are conducted using three datasets to verify the accuracy and robustness of our proposed method, MLRMC. The results demonstrate that our method outperforms six other classic feature matching methods.