Research on Real-Time Video Stitching Based on SURB Algorithm

Abstract

In view of the fact that ORB (the Oriented Fast and Rotated Brief) algorithm does not have scale invariance, an improved ORB algorithm, called SURB, was proposed combining the idea in Speed-up Robust Feature (SURF). Firstly, the Hessian matrix was used to detect feature points, which made the extracted feature points have scale invariance. Secondly, the ORB is used to describe feature points, which generated binary-descriptors of radiation invariant. Thirdly, the Hamming matrix is used for rough matching. Lastly, the method of RANSAC is used for purification and the average weighted algorithm is used for image fusion. When the image scale change, the average number of matching successful points of the SURB algorithm is three times of the ORB algorithm. However, when the image scale does not change, the average stitching time of ORB algorithm is same as the SURB algorithm and the average time-consuming of SURB algorithm from the feature detection to matching is six times of the SURF algorithm. The experimental results show that the SURB algorithm not only has the scale invariance, but also improves the matching efficiency, and the SURB can be applied to the video stitching system.