改进的概率假设密度滤波多目标检测前跟踪算法

基于概率假设密度滤波(Probability Hypothesis Density,PHD)的检测前跟踪(Track before detect,TBD)技术可以有效解决未知目标数的弱小点目标检测前跟踪问题.文章针对现有PHD-TBD算法存在目标数估计不准、目标发现延时较久的问题进行研究.从标准PHD滤波出发,更为合理地推导出PHD-TBD算法的粒子权重更新计算表达式,实现对目标数的准确估计；同时利用贝叶斯滤波理论,推导出基于量测的新生粒子概率密度采样函数,完成对目标的快速发现.仿真实验表明,与现有的PHD-TBD相比,改进算法能够适应目标扩散情况,准确估计目标数目,并实现对目标的快速发现和位置准确估计.

Improved multitarget track-before-detect using probability hypothesis density filter

Track-before-detect (TBD) technology based on the probability hypothesis density (PHD) filter can effectively solve the problem of tracking dim varying number multitarget. The existing PHD-TBD algorithm has two shortcomings, lack of accuracy in the number of targets and long time delay in responding to the targets being detected. The paper studied the PHD-TBD method, deduced the accurate expression of the updated particle weight of the PHD-TBD algorithm, and achieved the precise estimate of the number of targets. Simultaneously, by using Bayesian theory, it deduced the probability density sampling function of new born particles based on measurement, which can quickly and effectively find the targets. In addition, the simulation results demonstrate that the proposed algorithm can effectively estimate the number of targets, detect the targets and accurately estimate their positions with a more rapid speed compared with the existing PHD-TBD algorithm.