A Compensatory Algorithm for High-Speed Visual Object Tracking Based on Markov Chain

摘要

In order to effectively track high-speed objects in real time without any other instrumental methods but only based on computer vision, we propose an algorithm on camera control part by utilizing a history learning model in which a one-dimension Markov Transition Matrix synthesizes some historical information efficiently. The algorithm provides serials of conventional algorithms an effectively compensation when they perform worse in an interactive, high-speed circumstance, even lose the targets. Experimental results show that the new method is more stable and robust.