改进的多扩展目标PHD滤波算法

Improved Multi Extended Target PHD Filtering Algorithm

在扩展目标产生量测密度差异较大的情况下,传统的基于距离划分的多扩展目标高斯混合概率假设密度(ET-GM-PHD)滤波算法计算量大,跟踪效果不佳。针对这个问题,提出了一种改进的ET-GM-PHD滤波算法,该算法首先通过局部异常因子(LOF)检测对量测集进行杂波的滤除,然后采用共享最近邻(SNN)相似度为量测划分准则。SNN相似度体现了量测分布的局部信息,考虑了量测周围的量测信息,因此利用SNN相似度划分量测密度差别较大的量测集时,划分效果比较理想。提出的算法相较于传统算法,减少了运行时间,提升了跟踪的稳定性。

When the density of extended target producing varies greatly,the calculation of traditional multi extended target Gauss mixture probability hypothesis density( ET-GM-PHD) filtering algorithm based on the distance division is large,and the tracking effect is poor. To solve this problem,an improved ET-GM-PHD filtering algorithm is proposed. Firstly,the algorithm is filtered through the local outlier factor( LOF) detection set,and then an improved ET-GM-PHD filtering algorithm is obtained by using the shared nearest neighbor( SNN) similarity as the metric division criterion. SNN similarity reflects the local information of measurement distribution and considers the measurement information around the measurements. So,there is a better partitioning result of using the SNN similarity to divide the measurement sets when measurement density difference is great. The algorithm proposed can reduce the running time and improve the tracking stability compared with the traditional algorithm.