针对群目标跟踪数据关联的特点以及多目标跟踪数据关联经典的联合概率数据关联算法存在的计算量大与假设条件苛刻等问题,提出了基于群目标的多目标概率数据关联算法GJPDA(Group-target joint probability data association)。该算法首...针对群目标跟踪数据关联的特点以及多目标跟踪数据关联经典的联合概率数据关联算法存在的计算量大与假设条件苛刻等问题,提出了基于群目标的多目标概率数据关联算法GJPDA(Group-target joint probability data association)。该算法首先把跟踪空间内的所有回波看作一个群,跟踪空间中任一关联门内的所有回波看作一个子群,通过关联门是否交叉、多少回波位于关联门交叉区内的判别及其相对于不同关联中心概率的计算,确定交叉区域内回波的归属。以每一个关联门内所有回波的等效回波为量测实现多群目标跟踪。仿真结果表明了该算法的有效性。展开更多
The problem of forming validation regions or gates for new sensor measurements obtained when tracking targets in clutter is considered. Since the gate size is an integral part of the data association filter, this pape...The problem of forming validation regions or gates for new sensor measurements obtained when tracking targets in clutter is considered. Since the gate size is an integral part of the data association filter, this paper is intended to describe a way of estimating the gate size via the performance of the data association filter. That is, the gate size can be estimated by looking for the optimal performance of the data association filter. Simulations show that this estimation method of the gate size offers advantages over the common and classical estimation methods of the gate size, especially in a heavy clutter and/or false alarm environment.展开更多
文摘针对群目标跟踪数据关联的特点以及多目标跟踪数据关联经典的联合概率数据关联算法存在的计算量大与假设条件苛刻等问题,提出了基于群目标的多目标概率数据关联算法GJPDA(Group-target joint probability data association)。该算法首先把跟踪空间内的所有回波看作一个群,跟踪空间中任一关联门内的所有回波看作一个子群,通过关联门是否交叉、多少回波位于关联门交叉区内的判别及其相对于不同关联中心概率的计算,确定交叉区域内回波的归属。以每一个关联门内所有回波的等效回波为量测实现多群目标跟踪。仿真结果表明了该算法的有效性。
基金the National Natural Science Foundation of China (Grant No. 60672096)
文摘The problem of forming validation regions or gates for new sensor measurements obtained when tracking targets in clutter is considered. Since the gate size is an integral part of the data association filter, this paper is intended to describe a way of estimating the gate size via the performance of the data association filter. That is, the gate size can be estimated by looking for the optimal performance of the data association filter. Simulations show that this estimation method of the gate size offers advantages over the common and classical estimation methods of the gate size, especially in a heavy clutter and/or false alarm environment.
