Target recognition and tracking method based on multiple templates in complex scenes

Abstract

Image matching is a key technology in target recognition and tracking systems. This paper presents a method based on multi-template replacement strategy. The proposed method can ensure the resolution and accuracy of target recognition regardless of distance and field of view, and uses the idea of the Bayesian classifier. The problem of target recognition is converted into solving the Bayesian class posterior probability. This method was found to have high real-time performance and high target recognition accuracy. © 2013 Springer-Verlag.