基于变分贝叶斯的分布式融合目标跟踪
Distributed Fusion Target Tracking Based on Variational Bayes
- 电子学报 2022年50卷第5期 页码：1058-1065
- 作者机构：
1.河南大学人工智能学院, 河南郑州 450046
2.西北工业大学自动化学院，陕西西安 710129
- 作者简介：
[ "胡振涛 男，1979年6月出生， 河南永城人， 现为河南大学人工智能学院教授， 主要研究方向为复杂系统建模与估计， 运动目标跟踪.E‑mial: hzt@henu.edu.cn" ]
[ "杨诗博 男， 1997年9月出生， 河南开封人，现为河南大学人工智能学院硕士研究生， 主要研究方向为非线性估计， 变分贝叶斯估计.E‑mail: ysb@vip.henu.edu.cn" ]
[ "胡玉梅 女， 1990年10月出生， 河南永城人， 现为西北工业大学自动化学院博士研究生， 主要研究方向为变分贝叶斯估计， 运动目标跟踪.E‑mail: hym@mail.nwpu.edu.cn" ]
- 基金信息：国家自然科学基金(61976080;61771006);河南省科技攻关重点项目(212102310298);河南省教育厅科学技术研究重点项目(19A413006);河南大学研究生教育创新与质量提升计划项目(SYL20010101)
DOI：10.12263/DZXB.20210043
中图分类号： TP391收稿：2020-12-29，
修回：2021-02-08，
纸质出版：2022-05-25
- 稿件说明：
移动端阅览
胡振涛,杨诗博,胡玉梅等.基于变分贝叶斯的分布式融合目标跟踪[J].电子学报,2022,50(05):1058-1065.
HU Zhen-tao,YANG Shi-bo,HU Yu-mei,et al.Distributed Fusion Target Tracking Based on Variational Bayes[J].ACTA ELECTRONICA SINICA,2022,50(05):1058-1065.
胡振涛,杨诗博,胡玉梅等.基于变分贝叶斯的分布式融合目标跟踪[J].电子学报,2022,50(05):1058-1065. DOI： 10.12263/DZXB.20210043.
HU Zhen-tao,YANG Shi-bo,HU Yu-mei,et al.Distributed Fusion Target Tracking Based on Variational Bayes[J].ACTA ELECTRONICA SINICA,2022,50(05):1058-1065. DOI： 10.12263/DZXB.20210043.
摘要
考虑目标跟踪系统中未知时变过程噪声和随机异常量测噪声对目标状态估计精度的影响，本文提出了一种基于变分贝叶斯的分布式融合目标跟踪算法.首先在分布式融合框架下，结合变分贝叶斯机理利用逆威沙特分布和学生t分布，分别对无迹卡尔曼滤波实现中的一步预测协方差矩阵和量测似然概率密度函数进行建模；进而采用平均场变分理论近似解耦噪声分布参数和状态的联合概率密度函数，并通过定点迭代方法更新状态估计和噪声分布参数；最后依据协方差交叉融合策略实现对局部状态估计融合与修正.仿真结果表明，新算法综合考虑系统非线性、过程噪声时变性和量测噪声异常性的综合影响，能够有效提高运动目标的状态估计精度，同时具有较好的自适应性和鲁棒性．
Abstract
Considering the influence of unknown time-varying process noise and random abnormal measurement noise in the target tracking system
a new distributed fusion target tracking algorithm based on variational Bayes is proposed. Firstly
on each local platform of the distributed fusion structure
inverse-Wishart distribution and the Student's t distribution are chosen to model the error covariance of one-step prediction estimation and measurement likelihood in the unscented Kalman filter framework according to variational Bayes. And then
the joint probability density function of noise distribution parameters and state are approximately decoupled by mean field variational Bayesian theory
so that state estimation and noise distribution parameters can be updated by fixed-point iteration. Finally
we use the covariance intersection fusion strategy to fuse and correct all local state estimations. The simulation results show that the proposed algorithm
in which system nonlinearity
time-varying process noise and abnormal measurement noise are comprehensively considered
can effectively improve state estimation accuracy of moving targets
and has better adaptivity and robustness.
关键词
Keywords
references
韩崇昭 , 朱红艳 , 段战胜 . 多源信息融合 [M]. 北京 : 清华大学出版社 , 2010 : 32 ‑ 36 .
HAN C Z , ZHU H Y , DUAN Z S . Multi-source Information Fusion [M]. Beijing : Tsinghua University Press , 2010 : 32 ‑ 36 . (in Chinese)
DAVEY S J , FABRIZIO G A , RUTTEN M G . Detection and tracking of multipath targets in over-the-horizon radar [J]. IEEE Transactions on Aerospace and Electronic Systems , 2018 , 55 ( 5 ): 2277 ‑ 2295 .
YANG C , ZHENG J , REN X , et al . Multi-sensor Kalman filtering with intermittent measurements [J]. IEEE Transactions on Automatic Control , 2017 , 63 ( 3 ): 797 ‑ 804 .
潘泉 , 胡玉梅 , 兰华 , 等 . 信息融合理论研究进展:基于变分贝叶斯的联合优化 [J]. 自动化学报 , 2019 , 45 ( 7 ): 1207 ‑ 1223 .
PAN Q , HU Y M , LAN H , et al . Information fusion progress: joint optimization based on variational bayesian theory [J]. Acta Automatic Sinica , 2019 , 45 ( 7 ): 1207 ‑ 1223 . (in Chinese)
SHEN K , JING Z , DONG P . A consensus nonlinear filter with measurement uncertainty in distributed sensor networks [J]. IEEE Signal Processing Letters , 2017 , 24 ( 11 ): 1631 ‑ 1635 .
DONG P , JING Z , LEUNG H , et al . Robust consensus nonlinear information filter for distributed sensor networks with measurement outliers [J]. IEEE Transactions on Cybernetics , 2018 , 49 ( 10 ): 3731 ‑ 3743 .
殷旻佳 . 雷达/红外分布式融合滤波算法研究 [D]. 南京 : 南京理工大学 , 2017 .
YIN M J . Research on Radar/Infrared Distributed Fusion Filtering Algorithm [D]. Nanjing : Nanjing University of Science and Technology , 2017 . (in Chinese)
SARKKA S , NUMMENMAA A . Recursive noise adaptive Kalman filtering by variational Bayesian approximations [J]. IEEE Transactions on Automatic Control , 2009 , 54 ( 3 ): 596 ‑ 600 .
HUANG Y , ZHANG Y , WU Z , et al . A novel adaptive Kalman filter with inaccurate process and measurement noise covariance matrices [J]. IEEE Transactions on Automatic Control , 2017 , 63 ( 2 ): 594 ‑ 601 .
SARKKA S , HARTIKAINEN J . Non-linear noise adaptive Kalman filtering via variational bayes [C]// IEEE International Workshop on Machine Learning for Signal Processing . Southampton, UK : IEEE , 2013 .
HUANG Y , ZHANG Y , SHI P , et al . Robust Kalman filters based on Gaussian scale mixture distributions with application to target tracking [J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems , 2019 , 40 ( 9 ): 2082 ‑ 2096 .
NURMINEN H , ARDESHIRI T , PICHE R , et al . Skew-t filter and smoother with improved covariance matrix approximation [J]. IEEE Transactions on Signal Processing , 2018 , 66 ( 21 ): 5618 ‑ 5633 .
HUANG Y , ZHANG Y , Li N , et al . A novel robust student's t-based Kalman filter [J]. IEEE Transactions on Aerospace and Electronic Systems , 2017 , 53 ( 3 ): 1545 ‑ 1554 .
HUANG Y , ZHANG Y , ZHAO Y , et al . [J]. IEEE Transactions on Signal Processing , 2019 , 67 ( 13 ): 3606 ‑ 3620 .
SUN C , ZHANG Y , WANG G , et al . A new variational Bayesian adaptive extended Kalman filter for cooperative navigation [J]. Sensors , 2018 , 18 ( 8 ): 2538 .
DINI D H , MANDIC D P , JULIER S J . A widely linear complex unscented Kalman filter [J]. IEEE Signal Processing Letters , 2011 , 18 ( 11 ): 623 ‑ 626 .
0
浏览量
9
下载量
3
CSCD
- 网络PDF下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 技术支持由北京北大方正电子有限公司提供 京ICP备09064830号-19
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies