For being able to deal with the nonlinear or non-Gaussian problems, particle filters have been studied by many researchers. Based on particle filter, the extended Kalman filter (EKF) proposal function is applied to ...For being able to deal with the nonlinear or non-Gaussian problems, particle filters have been studied by many researchers. Based on particle filter, the extended Kalman filter (EKF) proposal function is applied to Bayesian target tracking. Markov chain Monte Carlo (MCMC) method, the resampling step, ere novel techniques are also introduced into Bayesian target tracking. And the simulation results confirm the improved particle filter with these techniques outperforms the basic one.展开更多
针对贝叶斯跟踪中目标状态的预测分布和后验分布,利用序列蒙特卡洛方法,基于多变量t-分布提出了一种新的粒子滤波算法,称之为t-分布粒子滤波器.为了根据样本估计目标状态的概率分布,提出了一种新的ECME算法,并嵌入到t-分布粒子滤波器中...针对贝叶斯跟踪中目标状态的预测分布和后验分布,利用序列蒙特卡洛方法,基于多变量t-分布提出了一种新的粒子滤波算法,称之为t-分布粒子滤波器.为了根据样本估计目标状态的概率分布,提出了一种新的ECME算法,并嵌入到t-分布粒子滤波器中.理论分析表明,在t-分布条件下,t-分布粒子滤波器是在样本数量上的渐近最优估计器.在机动目标跟踪实验中,比较了t-分布粒子滤波器、无色卡尔曼滤波(Unscented Kalm an filter)及自助式粒子滤波器(Bootstrap partic le filters)的跟踪精度.展开更多
基金This project was supported by the National Natural Science Foundation of China (50405017) .
文摘For being able to deal with the nonlinear or non-Gaussian problems, particle filters have been studied by many researchers. Based on particle filter, the extended Kalman filter (EKF) proposal function is applied to Bayesian target tracking. Markov chain Monte Carlo (MCMC) method, the resampling step, ere novel techniques are also introduced into Bayesian target tracking. And the simulation results confirm the improved particle filter with these techniques outperforms the basic one.
文摘针对贝叶斯跟踪中目标状态的预测分布和后验分布,利用序列蒙特卡洛方法,基于多变量t-分布提出了一种新的粒子滤波算法,称之为t-分布粒子滤波器.为了根据样本估计目标状态的概率分布,提出了一种新的ECME算法,并嵌入到t-分布粒子滤波器中.理论分析表明,在t-分布条件下,t-分布粒子滤波器是在样本数量上的渐近最优估计器.在机动目标跟踪实验中,比较了t-分布粒子滤波器、无色卡尔曼滤波(Unscented Kalm an filter)及自助式粒子滤波器(Bootstrap partic le filters)的跟踪精度.