基于信息散度的多无源传感器数据关联

Data association for multi-passive-sensor system based on information divergence

针对多无源传感器多维分配数据关联模型在构造关联代价时,未充分考虑位置估计不确定性所引入的误差问题,提出一种基于信息散度的数据关联算法.将伪量测信息的概率密度函数与真实观测数据的最大后验概率密度函数之间的差异性信息作为关联代价,并分别采用Kullback-Leibler散度和对称Kullback-Leibler散度来量化该差异.仿真分析结果表明,该算法具有良好的关联性能,其关联代价能更精准地反映数据关联的可能性程度.

The traditional multi-dimension assignment data association algorithm for the multi-passive-sensor data association algorithm has ignored the errors introduced by location localization estimation. Therefore, a data association algorithm is proposed based on information divergence. The differentia between the probability density function of pseudo measurements and the most posterior probability density function works as the association cost. The Kullback-Leibler divergence and symmetric Kullback-Leibler divergence are used respectively to quantify the differentia above. Finally, simulation results show that the proposed algorithm can achieve better performance and its association cost reflects the association probability more accurately.