一种改进的高斯混合概率假设密度滤波器

针对近邻目标场景下高斯混合概率假设密度滤波器的滤波精度较差问题,该文提出一种改进的高斯混合概率假设密度滤波器。基于更新后的目标强度中目标身份信息,首先将近似同一目标的多个高斯分量融合为一个新的高斯分量,然后依据目标检测结果对各目标分量的权重进行重新分配以获取一个精确的后验强度。实验结果表明,与相关近邻目标GM-PHD滤波器相比,该文算法的目标状态及数目估计精度具有较大优势,且其滤波性能相对稳定。

Aiming at the poor filtering accuracy of the Gaussian mixture probability hypothesis density filter in the close target scenarios,an improved Gaussian mixture probability hypothesis density filter is proposed in this paper.Based on the target identity information within the updated target intensity,first,the multiple Gaussian components approximating a same target are merged into a new Gaussian component,and then the weights of components of targets are redistributed according to the target detection result for the purpose of obtaining an accurate posterior intensity.The experimental results show that,compared with the related close target GM-PHD filters,the estimation accuracy of the target states and its number of the proposed algorithm has great advantages,and its filtering performance is relatively stable.