基于高斯混合概率假设滤波的水下目标跟踪算法

为了解决传统水下目标跟踪中目标数目估计不准确、状态估计误差增长过快的问题，提出了一种基于高斯混合概率假设滤波的水下目标跟踪算法。该算法基于双基地观测模型，采用高斯混合概率假设滤波算法处理方位和时延信息，利用粒子群算法处理多普勒频率获得矢量速度，进一步提升算法的跟踪精度。结果表明，该算法能完成在杂波环境下对目标的跟踪，相比传统的关联算法，能够有效地实现目标个数估计和抑制状态误差增长的目的。

Underwater target tracking algorithm based on Gaussian mixture probability hypothesis density filter

In order to solve the problem that number of targets estimated is inaccurate and error of state estimation increases too fast in traditional underwater target tracking, an underwater target tracking algorithm based on Gaussian mixture probability hypothesis density filtering is proposed. The algorithm is based on the bistatic observation model, which the Gaussian mixture probability hypothesis density filtering algorithm is used to bearings and time-delay information and particle swarm optimization algorithm is used to process the Doppler frequency to calculate the feedback vector velocity for improving the tracking accuracy of the algorithm. The results show that the algorithm can track targets in clutter environment, and can effectively achieve the purpose of estimating the number of targets and suppressing the growth of state estimation error compared with the traditional association algorithm.