基于GPU加速的粒子滤波多说话人跟踪算法及其应用

为了解决粒子滤波多说话人跟踪过程中粒子易发散导致多目标跟踪精度低的问题，提出了并行粒子滤波和基于GPU的K-均值聚类的多声源定位方法。该方法首先分析了粒子滤波在实现多目标跟踪时，进行数据关联的过程产生较大的计算量，并且出现多个目标时，粒子会逐渐发散。针对计算量大和粒子发散的问题，提出了一种并行粒子滤波和K-均值聚类的方法。实验表明，随着粒子数和目标数的增加，计算量以指数增加，并且粒子发散严重，采用基于GPU的K-均值聚类方法的粒子滤波多说话人跟踪方法，相比传统粒子滤波跟踪方法具有更收敛的粒子集并且跟踪精度较高。

Particle filter multi-speakers tracking algorithm based on GPU and its application

In order to solve the problem of low accuracy of multi-target tracking, particles in particle filter are easy to disperse in the process of multi-speaker tracking. This paper presented a parallel particle filter algorithm and GPU-based K-means clustering multi-source localization method. The method first analyzed the particle filter to achieve multi-target tracking, data association process have a large amount of computation, and the particles gradually diverge with the emergence of multiple targets. In order to solve the problem of large amount of computation and particle divergence, this paper proposed a method of parallel particle filter and k-means clustering. Experiments show that, as the number of particles and the number of targets increases, the amount of computation increases exponentially and the particles scatter seriously. In this paper, by using the GPU-based k-means clustering method, the particle filter multi-speaker tracking method has more convergent particle sets and higher tracking accuracy than the traditional particle filter tracking method.