GM-PHD滤波算法在IRST中的应用  

Application of GM-PHD Filtering Algorithm in IRST

作　　者：巩建坡[1,2] 陈闽[3] 周德召 程小亮[1] 

机构地区：[1]中国航空工业集团公司洛阳电光设备研究所,河南洛阳471000 [2]光电控制技术重点实验室,河南洛阳471000 [3]中国人民解放军驻六一三所军事代表室,河南洛阳471000

出　　处：《电光与控制》2016年第2期65-69,共5页Electronics Optics & Control

摘　　要：主要对基于有限随机集多目标跟踪算法进行研究,扩展了高斯混合概率假设密度(GM-PHD)滤波算法,提出适用于红外搜索跟踪(IRST)的非线性纯角度跟踪的GM-PHD算法。该算法对状态集和量测集进行贝叶斯估计,不需要数据关联,克服了传统的基于数据关联的多目标跟踪算法在强杂波、目标数目未知且不断变化的情况下数据关联困难的缺点,提高了IRST多目标跟踪性能的同时也能对目标个数进行实时估计。This paper focuses on multi-target tracking algorithm based on Random Finite Set （RFS）. The Gaussian Mixture Probability Hypothesis Density （GM-PHD） filtering algorithm is improved, and an algorithm based on GM-PHD is proposed, which can be used in Infrared Search and Track （IRST） system for nonlinear bearing-only tracking. The algorithm makes Bayes estimation to state set and measurement set, and no data association is needed. Therefore, the algorithm overcomes the problem of the traditional data association based multi-target tracking algorithm that it is difficult to make data association under the conditions of strong clutter and unknown/changing target number. It can improve the tracking ability of the IRST while making real-time estimation to the number of targets

关 键 词：多目标跟踪 红外搜索跟踪 有限随机集 最优滤波 高斯混合概率假设密度 

分 类 号：V271.4[航空宇航科学与技术—飞行器设计]