针对概率假设密度滤波器,提出一种基于熵分布的高斯混合实现算法.在该算法中,作为混合参数先验分布的熵分布,主要用在极大后验迭代过程中删减无关混合分量,该删减操作可通过混合权重调整来实现.此外,该算法还能够解决多个具有类似参数的混合分量共同描述一个强度峰值的问题.仿真结果表明,所提出算法优于典型的阈值删减算法. For the probability hypothesis density filter, an entropy distribution-based Gaussian mixture algorithm is proposed, in which the entropy distribution as a priori distribution of the mixing parameters is mainly used to cut off irrelevant mixed components during the maximum a posteriori iteration process, In addition, this algorithm can solve the problem that multiple mixed components with similar parameters describe an intensity peak together.The simulation results show that the proposed algorithm is superior to the typical threshold reduction algorithm .