Tracking of infrared radiation dim target based on mean-shift and particle filter

摘要

To effectively solve the problems of IR dim target tracking with complex background and the poorly effect of standard particle filter in this area, a complex tracking strategy based on Mean-Shift and particle filter is presented. As the combination of both advantages, the particles are sprayed over the position of maximum probability calculated by Mean-Shift algorithm for purpose of reducing the waste of particles and avoiding the loss of target. The utilization of particles is increased obviously, and thus it improves tracking procedure stability and robustness. Experiment results show that the combination algorithm can not only track dim target accurately with better real-time and tracking accuracy but also has a strong robustness for complex background interference.