首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于多模型和辅助粒子滤波的机动目标跟踪算法研究
引用本文:李景熹,王树宗,王航宇,宋振伟.基于多模型和辅助粒子滤波的机动目标跟踪算法研究[J].武汉理工大学学报(交通科学与工程版),2007,31(4):703-706.
作者姓名:李景熹  王树宗  王航宇  宋振伟
作者单位:1. 海军工程大学海军兵器新技术应用研究所,武汉,430033;海军驻426厂军代室,大连,116005
2. 海军工程大学海军兵器新技术应用研究所,武汉,430033
3. 海军工程大学电子工程学院,武汉,430033
4. 海军驻426厂军代室,大连,116005
摘    要:机动目标跟踪的本质是随机动态混合系统中的状态估计问题,其难点在于每一时刻运动模式的高度不确定性.在实际问题中,系统状态往往还呈现非线性、非高斯、不完全观测的特点.文中将多模型理论和辅助粒子滤波算法相结合,提出了一种新的机动目标跟踪算法——MM APF.仿真结果表明,该算法与传统的交互多模型——扩展卡尔曼滤波算法、辅助粒子滤波算法相比,在计算量相当的情况下,具有更高的滤波精度和较好的稳定性.

关 键 词:多模型  辅助粒子滤波  机动目标跟踪  混合系统
修稿时间:2007-04-16

Study on Maneuvering Target Tracking Algorithm Based on Multiple Model and Auxiliary Particle Filter
Li Jingxi,Wang Shuzong,Wang Hangyu,Song Zhenwei.Study on Maneuvering Target Tracking Algorithm Based on Multiple Model and Auxiliary Particle Filter[J].journal of wuhan university of technology(transportation science&engineering),2007,31(4):703-706.
Authors:Li Jingxi  Wang Shuzong  Wang Hangyu  Song Zhenwei
Institution:Institute for Application Study to Modern Technology of Naval Weapon, Naval Univ. of Engineering ,Wuhan 430033;Military Representatives of Naval Equipment Department in 426 Factory,Dalian 116005;Electronic Eng. College, Naval Univ. of Engineering,Wuhan 430033
Abstract:The essence of maneuvering target tracking is state estimation problem in stochastic dynamic hybrid system,and the main difficulty lies on the fact that maneuvering model at every step is of highly uncertainties.In practice,system state is always characterized by nonlinear,non Gaussian and incompletely observed.Combining multiple model theory and auxiliary particle filter algorithm,a new maneuvering target tracking algorithm called MMAPF is presented in the paper.Simulation results demonstrate that the MMAPF algorithm improves filtering accuracy,and has satisfied stability compared with IMM-EKF and APF algorithm.
Keywords:multiple model  auxiliary particle filter  maneuvering target tracking  hybrid system
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号