一种避免矩阵拆分的改进JPDA算法

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 , simula-tion results proved the effectiveness of the proposed algorithm .