基于瑞利熵的多无源传感器数据关联算法

针对当前多无源传感器数据关联算法构造关联代价时，未考虑位置估计不确定性所引入的误差，提出一种基于位置估计不确定性的被动传感器数据关联算法。首先通过量测与伪量测概率密度函数之间的瑞利熵构建关联代价函数，以准确描述两个相似的概率密度函数之间差异，然后通过具体实验测试本文算法的有效性和优越性。实验结果表明，相对于当前经典的数据关联算法，本文算法提高了数据关联的正确率和速度，具有更高的实际应用价值。

Data association for multi-passive-sensor system based on Renyi entropy

the data association model of multidimensional assignment did not consider the position estimation error in association cost, this paper proposed a Data association algorithm for passive sensor based on position estimation uncertainty. Rayleigh entropy is used to establish probability density function for the measurement and pseudo measurement to accurately describe the relationship, and describe two different probability density functions different, and the validity and superiority of this algorithm is test by simulation experiments. Simulation results show that, compared with the classical data association algorithm, this proposed algorithm can improve the rate of correct data association, and has higher practical application value.