An Improved FAST+SURF Fast Matching Algorithm

Target matching is an important part of image registration and mosaic. Based on a lot of real-time application requirements, the requirement of fast matching is also put forward. The classical matching algorithm has the problems of large computation and slow speed. Aiming at the problems existing in the classical algorithm, a fast matching algorithm based on the combination of FAST feature points and SURF descriptor is proposed. Experiments show that compared to the classic SIFT matching algorithm, the method is very good to achieve the goal of fast matching, in addition to the algorithm also improves the accuracy of the matching.