多尺度粒子滤波算法对目标状态估计的研究

翟永智

doi:10.15892/j.cnki.djzdxb.2011.04.034

2011 , Vol. 31 >Issue 4: 214 - 217

DOI: https://doi.org/10.15892/j.cnki.djzdxb.2011.04.034

摘要

当观测值给定的条件下,为了提取未知参数的信息,文中基于Gibbs与Metropolis-Hasting两种重要采样提出了多尺度粒子滤波算法。该算法在目标状态空间上一条马尔科夫链上,采用不同的粗细尺度进行交替采样来传递目标的状态信息和参数信息,从而搜索目标状态的最大后验分布函数。从而实现对机动目标状态的最优估计。其中细尺度采样保持了估算的精度,粗尺度提高了运算效率。仿真表明,该新算法实现了算法精度和效率的良好折衷。

关键词： 多尺度粒子滤波; 目标状态信息; 最大后验分布函数; 重要采样; 马尔可夫链

本文引用格式

翟永智 . 多尺度粒子滤波算法对目标状态估计的研究[J]. 弹箭与制导学报, 2011 , 31(4) : 214 -217 . DOI: 10.15892/j.cnki.djzdxb.2011.04.034

Abstract

Based on the given observation data, the multi-scale filtering algorithm was proposed for extracting optimum value with respect to the target state by using different fine and coarse scales in a single chain to explore a maximum posterior likelihood distribution function of the state information. Hence, the state information concerning maneuvering target optimum estimation can be achieved via the novel algorithm based on both Gibbs and Metropolis-Hasting important sampling. The fine scales guaranteed the precision of estimation while the coarse scales enhanced computational efficiency. The simulation shows the fact that the good tradeoff between the estimation accuracy and computational efficiency.

Key words： multi-scale particle filtering; target state information; maximum posterior distribution function; important sampling; Markov chain

[an error occurred while processing this directive]

参考文献

[1]	MK Pitt, N Shephard. Filtering via simulation: Auxiliary particle filters[J]. Jourmal of the American Statistical Association, 1999, 94(446): 590-599.
[2]	A Doucet. On sequence simulation-based method for Bayesian filtering [R]. Dept. Eng., Univ. Cambrige. U. K.: Tech. Rep. CUED/F-IFENG/IR. 310, 1998.
[3]	C Adrieu, A Doucet, S Godsill. On sequential Monte Carlo sampling methods for Bayesian filtering [R]. Dept. Eng., Univ. Cambrige. U. K.: Tech. Rep. U. K., 1999.
[4]	A Doucet, N J Gordon, Krishnamuethy. Particle filter for state estimation of jump Markov linear systems [R]. Tech. Rep. Defence Eval. Res. Agency., 1999.
[5]	J S liu, Chen Yong. Sequence Monte Carlo method for dynamic systems [R]. Tech Dept. Stat. Univ. Stanford. CA., 1998.
[6]	F J FLORIS, M D Bush, M Cuypers, et al. Comparison of production forecast uncertainty quantification methods an integrated study [C]// Proc. 1st Symp. Petroleum Geostatic. Toulouse. France. Apr. 20-23, 1999.
[7]	J W Barker, M Cuypers, L Holdden. Quantifying uncertainty in production forecasts: Another look at the PUNQ-S3 problem [C]// Proc, Soc. Petroleum Eng. annu. Tech. Conf., 2000.
[8]	Dave Higdon, Herbert Lee, Zhouxin Bi. A Bayesian approach to charactering uncertainty in inverse problems using coarse and fine-scale information[J]. IEEE Trans. Signal Process, 2007, 50(2): 389-398.
[9]	Matthew Orton, William Fitzgerald. A Bayesian approach to tracking multiple targets using sensor arrays and particle filters [J]. IEEE Trans. Signal Process., 2002, 50(2): 216-223.

Options

文章导航