基于PHD滤波的箱粒子划分多目标跟踪算法  

A Multi-target Tracking Algorithm Based on Box Particle Dividing PHD Filter

作　　者：吴孙勇[1,2] 宁巧娇 蔡如华 刘义强[1] 孙希延 WU Sun-yong1,2, NING Qiao-jiao 1, CAI Ru-hua1, LIU Yi-qiang1,SUN Xi-yan2(1.School of Mathematics and Computing Science, Guilin University of Electronic Technology, Guilin 541004, China; 2. Guangxi Key Laboratory of Precision Navigation Technology and Application, Guilin 541004, Chin)

机构地区：[1]桂林电子科技大学数学与计算科学学院,广西桂林541004 [2]广西精密导航技术与应用重点实验室,广西桂林541004

出　　处：《电光与控制》2018年第5期12-16,共5页Electronics Optics & Control

基　　金：国家自然科学基金(61561016;61362005);广西自然科学基金(2016GXNSFAA380073;2014GXNSFAA118352;2014GXNSFBA118280);广西精密导航技术与应用重点实验室基金(DH201502);广西密码学与信息安全重点实验室研究课题项目(GCIS201611);广西高校数据分析与计算重点实验室开放基金

摘　　要：针对现有箱粒子概率假设密度(BOX-PHD)滤波存在箱粒子冗余问题,提出一种箱粒子划分的概率假设密度滤波多目标跟踪算法。该算法在目标状态估计的更新阶段之前,将预测得到的每一个箱粒子划分成多个箱粒子,从而得到等价的箱粒子集,然后对这些箱粒子集的权值利用区间量测进行更新,从而估计目标的状态及数目。该划分由于将箱粒子划分更小,能更好地利用区间量测信息,可以有效避免箱粒子因压缩不足而导致的估计有偏情况。仿真结果表明所提方法可以有效地提高目标的跟踪性能。To solve the problem of box particle redundancy in existing Box Particle Probability Hypothesis Density（ BOX-PHD） filter,a new multi-target tracking algorithm based on box particle dividing PHD filter is proposed. Before the update stage of the target state estimation,each box particle obtained from prediction is divided into several sub-box particles to obtain the equivalent box particle subsets. Then,by using interval measurement,the weights of these box particle subsets are updated to estimate the state and number of the targets. The interval measurement information can be better used because the box particle is divided smaller.Also,the biased estimation caused by the insufficient compression of box particles can be effectively avoided. Simulation results show that the proposed method can effectively improve the target tracking performance.

关 键 词：多目标跟踪 箱粒子 区间分析 概率假设密度滤波 箱粒子划分 

分 类 号：TN953[电子电信—信号与信息处理]