The Optimized ORB Algorithm Based on Region Partition

Abstract

Aiming at the problems of low matching accuracy and slow matching speed of ORB feature matching algorithm under complex environments, an improved ORB algorithm based on region division and RANSAC algorithm was proposed. By dividing the image into regions, the similarity algorithm is used to extract the regions with high similarity, then the ORB algorithm is used to extract the feature points of similar regions. The results can effectively improve the operation efficiency of image feature point extraction. The improved ORB algorithm combined with RANSAC algorithm to eliminate the wrong matching point pairs that get more accurate matching results. Experimental results show that compared with the original method, the improved algorithm has better accuracy and real-time performance.