一种基于多目标跟踪的改进概率数据关联算法  

An Improved Probabilistic Data Association Algorithm Based on Multi-Target Tracking

作　　者：贾正望[1] 张华阳[1] 

机构地区：[1]中国电子科技集团公司第二十八研究所,南京210007

出　　处：《指挥信息系统与技术》2010年第3期36-40,共5页Command Information System and Technology

摘　　要：针对联合概率数据关联算法过于复杂以及密集多目标处理中的问题,文中提出了一种适用于实际应用的改进概率关联算法,该算法通过引进雷达多普勒测量信息,对进入跟踪门相交区域中的公共测量值权重系数进行调整,以提高关联精度,从而使最终的估计值更加准确。理论分析和蒙特卡罗仿真结果表明,该算法具有较小的计算量以及良好的跟踪性能。To solve the complexity of joint probabilistic data association algorithm and the problems in the process of multiple close targets, an improved probabilistic data association algorithm suitable for the practical application is proposed. This algorithm incorporates radar Doppler measurement information and modifies weighting of state estimation of measurements in the common region of tracking gates to improve the association accuracy, consequently, to make the final estimation more accurate. The theoretical analysis and Monte-Carlo simulation results show that the algorithm has low computation costs and better real-time tracking performance.

关 键 词：多目标跟踪 数据关联 概率数据关联算法 

分 类 号：TN957.52[电子电信—信号与信息处理]