一种避免矩阵拆分的改进JPDA算法  

A Modified Algorithm of Joint Probabilistic Data Association Avoiding Matrix Splitting

作　　者：石汪权 袁富宇[1] 蒲勇[1] 

机构地区：[1]江苏自动化研究所,江苏连云港222061

出　　处：《指挥控制与仿真》2017年第6期47-52,共6页Command Control & Simulation

摘　　要：联合概率数据关联(JPDA)算法是杂波环境下多目标跟踪的一种非常有效的算法,但该算法在目标密集或回波数较多时实时性较差,不能满足某些复杂的多目标跟踪应用场景。针对此问题,提出了一种避免矩阵拆分的改进JPDA算法,简化了关联概率的计算,从而提高了JPDA算法的实时性,仿真实验证明了改进算法的有效性。The Joint Probabilistic Data Association Algorithm is highly effective for multiple targets tracking in clutter,but its real-time is poor in dense targets or echo environment,so that it can not satisfy some complex scenario of multiple targets tracking. A modified JPDA algorithm is proposed to solve the problem. In the proposed algorithm,the process of splitting the validation matrix is avoided,so the calculation of association probability is simplified and the real-time is improved,simulation results proved the effectiveness of the proposed algorithm.

关 键 词：数据关联 多目标跟踪 矩阵拆分 

分 类 号：E911[军事] E917