Infrared Target Tracking Based on Adaptive Particle Filter
基于自适应粒子滤波的红外目标跟踪

For tracking infrared target in non-linear condition,an adaptive particle filtering algorithm was presented.A weighted probability model of target was established.During the filtering,a resampling method based on bi-process was proposed.On basis of the method,an adaptive adjustment to sampled particle-set was formed,which resolves efficiently particles degeneration.To valuate the efficiency of the proposed algorithm,it was applied to the real infrared image sequence tracking.Experiment result shows,in non-linear condition,in comparison with traditional FP and EKF,the proposed algorithm have great advantages in the field.