用于机动目标跟踪的多模型概率假设密度滤波器

王晓; 韩崇昭

您当前的位置：

首页 >

文章列表页 >

用于机动目标跟踪的多模型概率假设密度滤波器

更新时间：2025-07-09

- 用于机动目标跟踪的多模型概率假设密度滤波器
- A Probability Hypothesis Density Filter with Multiple Models for Maneuvering Target Tracking
- 西安交通大学学报 2011年45卷第12期页码：1-5
- 作者机构：
  
  西安交通大学电子与信息工程学院,西安,710049
- 作者简介：
- 基金信息：
  
  : 2011-04-25. 作者简介: 王晓(1978-),男,博士生;韩崇昭(通信作者),男,教授,博士生导师. 基金项目: 国家自然科学基金创新研究群体科学基金资助项目(60921003);国家“973计划”资助项目(2007CB311006);国家自然科学基金资助项目(61074176)
- DOI：
  中图分类号： TP274
- 网络首发：2011-12-10，
  
  纸质出版：2011
- 稿件说明：
移动端阅览
王晓, 韩崇昭. 用于机动目标跟踪的多模型概率假设密度滤波器[J]. 西安交通大学学报, 2011,45(12):1-5.

A Probability Hypothesis Density Filter with Multiple Models for Maneuvering Target Tracking[J]. 2011, 45(12): 1-5.
王晓, 韩崇昭. 用于机动目标跟踪的多模型概率假设密度滤波器[J]. 西安交通大学学报, 2011,45(12):1-5. DOI：

A Probability Hypothesis Density Filter with Multiple Models for Maneuvering Target Tracking[J]. 2011, 45(12): 1-5. DOI：

摘要

针对概率假设密度(PHD)滤波器在多目标跟踪问题中无法解决目标发生较大机动时的目标丢失问题

提出了一种多模型概率假设密度(MM-PHD)滤波器.这种MM-PHD滤波器在粒子PHD滤波器的基础上

使用多模型方法对滤波器中每个描述目标状态的粒子的状态进行更新

再将更新后的粒子代入传统的PHD滤波器中用于估计目标的PHD的分布.该滤波器结合PHD滤波器和多模型方法的特点

可用于目标数未知的多机动目标跟踪

且对目标的数量和状态的估计更加准确.多机动目标跟踪的仿真实验表明

与已有方法相比

该滤波器对目标数的估计与真实情况基本一致

描述多目标状态估计误差的Wasserstein距离值降低了50%以上.

Abstract

A multiple model probability hypothesis density(MM-PHD)filter is proposed to solve the track loss problem of PHD filter in highly maneuvering targets tracking. The MM-PHD filter bases on the particle PHD filter

and updates the state of the particles using the multiple model method. Then the updated state of the particles is used to evaluate the PHD distribution of the targets. The filter combines the features of both the PHD filter and the multiple model method and can deal with multi-targets' maneuvering with the number of targets unknown. The proposed filter estimates the number and the state of the targets more accurately than the existing filters do. Simulation results and comparisons with existing algorithms show that the number of targets estimated by the proposed algorithm is consistent with the real situation and the Wasserstein distance value that describes the estimation error decreases more than 50%.

关键词

Keywords

references

潘泉, 叶西宁, 张洪才. 广义概率数据关联算法[J]. 电子学报,2005,33(3):467-472.

PAN Quan, YE Xining, ZHANG Hongcai. Generalized probability data association algorithm[J]. Acta Electronica Sinica, 2005,33(3):467-472.

韩崇昭, 李晨, 朱洪艳. 红外搜索跟踪系统的数据关联算法研究[J]. 控制与决策,2008,28(2):171-176.

HAN Chongzhao, LI Chen, ZHU Hongyan. Data association algorithm of infrared search and track system[J]. Control and Decision, 2008,28(2):171-176.

MAHLER R P S. Multitarget Bayes filtering via first-order multitarget moments [J]. IEEE Transactions on Aerospace and Electronic System, 2003, 39(4): 1152-1178.

VO B N, SINGH S, DOUCTE A. Sequential Monte Carlo methods for multi-target filtering with random finite sets [J]. IEEE Transactions on Aerospace and Electronic System, 2005, 41(4): 1224-1245.

VO B N, MA Wingkin. The Gaussian mixture probability hypothesis density filter [J]. IEEE Transactions on Signal Processing, 2006, 54(11): 4091-4104.

PUNITHAKUMAR K, KIRUBARAJAN T, SINHA A. Multiple-model probability hypothesis density filter for tracking maneuvering targets [J]. IEEE Transactions on Aerospace and Electronic System, 2008, 44(1):87-98.

GORDON N J, SALMOND D J, SMITH A F M. Novel approach to nonlinear/non-Gaussian Bayesian state estimation [J]. IEE Proceedings: F, 1993, 140(2): 107-113.

ARULAMPALAM S, MASKELL S, GORDON N, et al. A tutorial on particle filters for on-line nonlinear/non-Gaussian Bayesian tracking [J]. IEEE Transactions on Signal Process, 2002, 50(2):174-188.

LI Xiaorong, JILKOV V P. Survey of maneuvering target tracking: part V Multiple-model methods [J]. IEEE Transactions on Aerospace and Electronic System, 2005, 41(4):1255-1321.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

概率假设密度滤波的谱聚类目标状态提取方法

采用结构自适应窗的非局部均值图像去噪算法

一种用于杂波中机动目标跟踪的自适应关联波门设计方法

拓展目标量测集合分割算法

面向离合器接合过程控制的不确定性估计