针对杂波环境下高斯混合粒子PHD跟踪精度低,滤波发散的问题,提出基于模糊混合退火分布的高斯混合粒子PHD。所提算法在传统的高斯混合粒子PHD滤波的基础上,采取状态变量分解和引入退火参数产生建议分布函数,同时采用模糊推理系统产生最优的退火系数,有利于提高粒子滤波的稳定性和精度,然后对PHD进行更新。仿真结果表明:该算法能在杂波环境下有效跟踪多个目标,与高斯混合粒子PHD滤波相比,状态估计更加接近真实值,大大提高了跟踪精度和系统稳定性。

In order to overcome lower estimating accuracy and filtering divergence of traditional GMP-PHD algorithm in clutter environment, a new improved GMP-PHD is proposed in this paper, which based on fuzzy hybrid annealed distribution. Compared with the traditional GMP-PHD, the algorithm adopts the state variable decomposition and the introduction of annealing parameters to generate the proposed distribution fuction, and the optimal annealing coefficient is generated by the fuzzy inference system, which could improve the stability and accuracy of particle filter, and then to update a PHD. The simulation show that the improved algorithm can effectively track multiple targets in clutter environment, compared with GMP-PHD filter, closer to the true value, improves the tracking accuracy and system stability.