基于核密度估计高斯混合PHD滤波的多目标跟踪算法  

Multi-target tracking algorithm based on kernel density estimation Gaussian mixture PHD filter

作　　者：周卫东[1] 张鹤冰[1] 乔相伟[1] 

机构地区：[1]哈尔滨工程大学自动化学院,黑龙江哈尔滨150001

出　　处：《系统工程与电子技术》2011年第9期1932-1936,共5页Systems Engineering and Electronics

摘　　要：针对多目标跟踪系统中传统算法目标估计精度较低的问题,提出了基于核密度估计的高斯混合概率假设密度(probability hypothesis density,PHD)滤波算法。在该算法中,经过剪枝、合并后,引入核密度估计理论的Mean-shift算法,对高斯混合PHD分布密度函数进行核密度估计,取代了传统算法中的状态估计方法。最后,选择估计后得到的峰值作为目标状态估计值。仿真结果表明,基于核密度估计的高斯混合PHD滤波算法比传统算法具有更高的估计精度。Considering the lower estimated accuracy of traditional algorithms in multi-target tracking system, a Gaussian mixture probability hypothesis density （PHD） filtering algorithm based on kernel density estimation is proposed. After pruning and merging in this algorithm, the Mean-shift algorithm is introduced to estimate kernel density of Gaussian mixture PHD distribution density function, which replaces the traditional state estimation methods. Finally, the estimated peak value is used as the state value. Simulation results show that compared with the traditional algorithms, the proposed algorithm has a higher tracking accuracy.

关 键 词：多目标跟踪 概率假设密度 随机集 Mean—shift算法 

分 类 号：TN911[电子电信—通信与信息系统]