An Improved ORB Feature Point Matching Algorithm

ORB, a very fast binary descriptor based on BRIEF, which is rotation invariant and resistant to noise. To solve the problem that the traditional ORB feature descriptor does not have scale invariance, an improved ORB feature point matching algorithm which borrowing the idea of Binary Robust Invariant Scalable Keypoints (BRISK) algorithm to uniformly sample the extracted feature points is proposed in this paper. The experimental results show that the algorithm not only inherits the advantages of the high speed from ORB algorithm but also has good scale invariance. It is suitable for applications requiring high real-time and large scale changes.