基于修正贝努利滤波的被动多目标跟踪算法  

Passive multi-target tracking based on modified MeMBer filter

作　　者：钟茜怡[1] 姬红兵[1] 欧阳成[1] 

机构地区：[1]西安电子科技大学电子工程学院,陕西西安710071

出　　处：《系统工程与电子技术》2012年第8期1549-1554,共6页Systems Engineering and Electronics

基　　金：国家自然科学基金(60871074)资助课题

摘　　要：针对势平衡多目标多贝努利(cardinality balanced multi-target multi-Bernoulli,CBMeMBer)滤波中的量测信息弱化问题,提出一种改进的多目标多贝努利(improved multi-target multi-Bernoulli,IMeMBer)滤波。该算法通过对漏检目标的多贝努利随机集进行修正,在解决目标数过估问题的同时,避免了CBMeMBer滤波中的量测信息弱化问题。在此基础上,将高斯粒子滤波引入IMeMBer算法中,通过一组高斯粒子近似多贝努利随机集中元素的概率分布,实现被动测角情况下的多目标跟踪。仿真结果表明,所提算法能够以较小的运算代价达到高斯混合粒子劳势估计的概率假设密度滤波相似的跟踪精度,具有良好的工程应用前景。To solve the measurement innovation weakening problem in the cardinality balanced multi-target multi-Bernoulli（CBMeMBer） filter, an improved multi-target multi-Bernoulli （MeMBer） filter is proposed by modifying the legacy rather than the measurement updated tracks parameters. Then, to provide a closed-form solution to the nonlinear problem occurred in the passive bearings-only multi-target tracking system, a set of Gaussian particles is employed to approximate the distributions of the multi-Bernoulli random finite set. The simulation results show that the proposed algorithm can get nearly the same tracking accuracy as that of the Gaussian mixture particle-cardinalized probability hypothesis density filter with the much lower computational cost, implying good application prospects.

关 键 词：随机有限集 概率假设密度滤波 多目标多贝努利滤波 多目标跟踪 

分 类 号：TN953[电子电信—信号与信息处理]