An Improved ORB Feature Point Image Matching Method Based on PSO

摘要

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 resultof ORB algorithm is lack of robustness. In this paper, we proposed an improved ORB algorithm based on PSO (ParticleSwarm Optimization) algorithm. Firstly, ORB algorithm was used to detect image feature points. Secondly, distancesimilarity 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 resultsshowed that the improved algorithm can effectively improve the accuracy of image matching and expand the scope ofapplication of the algorithm.