An improved ORB feature point image matching method based on PSO

Abstract

ORB (Oriented FAST and Rotated BRIEF) algorithm is widely used in feature point matching with images. However, the randomness of the threshold of search strategy makes the matching result inaccurate. The matching result of ORB algorithm is lack of robustness. In this paper, we proposed an improved ORB algorithm based on PSO (Particle Swarm Optimization) algorithm. Firstly, ORB algorithm was used to detect image feature points. Secondly, distance similarity measurement is applied to ORB and orientation constraint was added to reduce mismatching rate. Finally, particle swarm optimization algorithm was used to optimize the threshold of search strategy. Experimental results showed that the improved algorithm can effectively improve the accuracy of image matching and expand the scope of application of the algorithm.