[1]刘叶楠,张峰.一种改进的交互式多模型粒子滤波算法[J].机械与电子,2018,(09):3-6.
　LIU Yenan,ZHANG Feng.An Improved Interactive Multimodel Particle Filter Algorithm[J].Machinery & Electronics,2018,(09):3-6.
点击复制

一种改进的交互式多模型粒子滤波算法()
分享到：

机械与电子[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2018年09期
页码:
3-6
栏目:
设计与研究
出版日期:
2018-09-24

文章信息/Info

Title:
An Improved Interactive Multimodel Particle Filter Algorithm
文章编号:
1001-2257(2018)09-0003-04
作者:
刘叶楠; 张峰
(西安工业大学电子信息工程学院,陕西 西安 710021 )
Author(s):
LIU Yenan; ZHANG Feng
(School of Electronic Information Engineering, Xi’an Technological University, Xi’an 710021, China)
关键词:
机动目标; 人工智能; 迭代容积; 交互式多模型
Keywords:
maneuvering target;  artificial intelligence;  iterative volume ;  interacting multiple model
分类号:
TP301
文献标志码:
A
摘要:
在实际的目标跟踪与识别的过程中，机动目标的跟踪不仅受非线性和非高斯现象的影响，而且它所采用的交互式多模型粒子滤波算法还存在着粒子权值退化和重要性密度函数选择的问题，导致跟踪误差较大。针对这一问题，提出了一种交互式的多模型的迭代容积粒子算法。该算法通过融合最新量测值产生更加接近系统的真实值，从而使粒子利用率得到进一步的提高。此外为了解决粒子的多样性减少的问题，还引入了MCMC重采样方法。仿真的结果表明，对于机动目标的跟踪与识别，改进的算法的精度要比IMM-PF算法的精度高、误差小，且通过改进的算法得到的重要性密度函数更加接近系统的后验概率分布。
Abstract:
There are a large number of nonlinear and non- gaussian phenomena in the tracking of maneuvering target, and The interacting multiple model particle filter algorithm has the problem of particle weight degradation and importance density function selection. It leads to the increase of tracking error. The paper introduces the iterative volume particle filter algorithm for this problem. The algorithm can get a posteriori probability distribution that is close to the real value of the system and increase the utilization of particle by Iterative volume filtering algorithm fusing the latest measurement values. It can alleviate the decrease of particle diversity through adding the MCMC resampling step. Simulatio n shows that the tracking accuracy of the improved algorithm is higher than that of the IMM-PF algorithm in the case of the turning maneuver of the target. The importance density function generated by the improved algorithm is closer to the posterior probability distribution of the system, and the tracking error is less than IMM-PF algorithm.

参考文献/References:

[1]Pan Q, Jia Y G, Zhang H C. A d-step fixed-lag smoothing algorithm for Markovian switching systems[C]// Proceedings of the Fifth International Conference on Information Fusion,2002:721-726.

[2]吴凡.基于非线性滤波的机动目标跟踪算法研究[D].西安:西安电子科技大学, 2010.

[3]Gordon N J,Salmond D J,Smith A F M. Novel approach to nonlinear/non-Gaussian Bayesian state estimation[J].IEE Proceedings-F Radar and Signal Processing, 1993, 140(2):107-113.

[4]Kim H S, Kim I S, Chun S Y.Design of fuzzy interacting multiple model algorithm for maneuvering target tracking[C]// 30th Annual Conference of IEEE Industrial Electronics Society,2004:2092-2097.

[5]孙枫, 唐李军.Cubature粒子滤波[J].系统工程与电子技术, 2011,33(11):2554-2557.

[6]王华剑, 景占荣, 郑文泉,等.迭代容积卡尔曼粒子滤波算法[J].东南大学学报(自然科学版), 2013, 43(增刊1):85-88.

[7]蔡宗平,戴定成,牛创.基于容积粒子滤波的交互式多模型算法[J].系统工程与电子技术,2014,36(12):2366-2370.

[8]张荣刚,顾强.基于ViBe的动态目标检测算法优化[J].机械与电子, 2017, 35(4):21-26.

[9]Arasaratnam I,Haykin S . Cubature Kalman filters[J].IEEE Transactions on Automatic Control, 2009, 54(6):1254-1269.

[10]Arasaratnam I, Haykin S, Hurd T R. Cubature Kalman filtering for continuous-discrete systems: theory and simulations[J]. IEEE Transactions on Signal Processing, 2010, 58(10):4977-4993.

[11]王婷婷,李戈,赵杰,等.基于双目视觉的运动目标检测跟踪与定位[J].机械与电子, 2015(6):73-76.

相似文献/References:

[1]肖倩宏,康 鹏,杜 江,等.深度学习在电网智能调控系统中应用研究[J].机械与电子,2021,(01):38.
　XIAO Qianhong,KANG Peng,DU Jiang,et al.Research on the Application of Deep Learning Theory in Power Grid Intelligent Dispatching[J].Machinery & Electronics,2021,(09):38.
[2]裴 俊,李林锐,邹敏佳,等.基于人工智能的配网网络发令系统及应用[J].机械与电子,2021,(03):75.
　PEI Jun,LI Linrui,ZOU Minjia,et al.A System Design of Digital -based Commanding of Power Dispatch Based on Artificial Intelligence[J].Machinery & Electronics,2021,(09):75.
[3]单连飞,张 越.电网调度专业语料库构建方法研究及应用[J].机械与电子,2022,(04):73.
　SHAN Lianfei,ZHANG Yue.Research and Application for Construction Method of Power Grid Dispatching Professional Corpus[J].Machinery & Electronics,2022,(09):73.

备注/Memo

备注/Memo:
基金项目：国家自然科学基金资助项目(61271362)；陕西省科技厅一般项目-工业领域(2017GY-081)；陕西省自然科学基金(2017JM6041)；西安市科技计划项目(CXY1341(1))；陕西省教育厅科技专项(2017JK0373)
作者简介：刘叶楠（1987-），男，汉族，河北唐山人，助教，研究方向为智能控制、模式识别等；张峰（1979-），男，汉族，河南郑州人，教授，研究生导师，研究方向为信号处理、自动控制等。
更新日期/Last Update: 2019-10-31