论文部分内容阅读
对多运动模型的目标进行跟踪,通常采用传统的交互式多模型粒子滤波算法。但是,该算法存在一些缺陷和不足。为此,提出了一种新的基于变速率模型和遗传算法的IMMPF目标跟踪算法。针对IMMPF算法对目标进行跟踪时可能出现的未知可变转弯速率,采用了一种更恰当的可变速率目标模型;对于IMMPF算法中的粒子多样性丧失问题,则将进化理论中的遗传算法引入到目标跟踪算法中,对采样进行优化,增加了采样粒子的多样性,使采样向后验分布取值较大的区域移动。仿真结果表明,提出的算法能更好的适应目标的机动运动,同时明显减少所需的采样数,取得了更好的跟踪性能。
To track the targets of multi-sport models, the traditional interactive multi-model particle filtering algorithm is usually adopted. However, the algorithm has some shortcomings and deficiencies. Therefore, a new IMMPF target tracking algorithm based on variable rate model and genetic algorithm is proposed. Aiming at the unknown variable turning rate that may occur when the IMMPF algorithm tracks the target, a more appropriate target model of variable rate is adopted. For the problem of loss of particle diversity in the IMMPF algorithm, the genetic algorithm in evolutionary theory is introduced To the target tracking algorithm, the sampling is optimized, increasing the diversity of sampling particles, so that the sample to the posterior distribution of a larger value of the region to move. The simulation results show that the proposed algorithm can better adapt to the target maneuvering motion, while significantly reducing the number of samples required and achieving better tracking performance.