摘要
进化粒子滤波算法通过模仿生物进化体制,以牺牲大量的计算量为代价增加样本集的多样性,从而较好地缓解了样本贫化现象。将进化粒子滤波算法应用于雷达目标跟踪过程中,变异强度的选择参考系统噪声与观测噪声性质,并通过粒子匮乏现象的强弱选择是否应用进化算法,从而大大减少了计算量。仿真结果显示所提出的算法对雷达目标跟踪有较好的应用价值。
Through imitating biology evolvement,at the cost of much calculation, evolutionary particle filter algorithm ameliorates the diversity of samples set to relieve the effect caused by samples impoverishment.Based on state noise and observation,an advanced evolutionary particle filter algorithm is put forward,and precision is improved.What s more,extent of samples impoverishment determines if to proceed the algorithm,so the calculation mount is largely reduced.Simulation results demonstrate the feasibility of ...
出处
《现代防御技术》
北大核心
2008年第2期115-118,123,共5页
Modern Defence Technology
基金
国家自然科学基金项目(60572038)
关键词
粒子滤波算法
进化算法
目标跟踪
particle filter algorithm
evolutionary algorithm
target tracking