具有形状信息的多个群目标跟踪算法

摘要

Aiming at the problem of low shape estimation accuracy under the condition of miss detection and clutter measurements in multiple group-target tracking,a novel multiple group-target tracking algorithm with shape information is proposed in this paper.Firstly,the algorithm divides the measurement set for track initiation.Then,the method improves the conventional group-target Bayesian recursive estimation,and fuses the group-target track association algorithm.Based on the improved method,the kinematic state and shape information of group-target can be estimated simultaneously,and high shape estimation accuracy is achieved.Simulation results show that the algorithm can not only track multiple group-targets simultaneously,but also achieve the shape information of each group-target with high shape estimation accuracy.%针对杂波和漏检环境下多个群目标跟踪中形状估计精度低的问题,提出一种具有形状信息的多个群目标跟踪算法.该算法首先进行量测集划分进而起始航迹,随后对传统的群目标Bayesian递推算法进行改进,并融合群航迹关联等算法,利用改进的算法对多个群目标的运动状态和形状信息同时进行估计,大大提高了形状的估计精度.仿真结果表明,该算法不仅可以对多个群目标的运动状态同时进行跟踪,并且可以有效估计每个群目标的形状信息,大大提高了形状估计精度.