A scene matching algorithm based on SURF feature

Abstract

Scene matching has found important and wide applications in imaging guidance of cruise missile. A scene matching algorithm based on SURF feature is proposed in this paper. Firstly, SURF feature points are extracted respectively from base image and real-time image. Then, a coarse-to-fine matching method is used to realize the match of SURF feature points. The proposed algorithm has been tested on the collected image set. The experimental results shows that, compared with the frequently-used normal cross-correlation method, the proposed algorithm can process more complicated geometric deformations existed between base image and real image and acquire higher matching accuracy; compared with the matching algorithm based on SIFT feature, the proposed algorithm has lower computational burden and faster processing speed, which can meet the real-time requirements for scene matching.