CAJ | 학술논문

多维分配模型在构造关联代价函数时，直接利用极大似然估计值代替目标的真实位置信息，未考虑极大似然估计所引入的随机误差。针对此问题，提出一种基于瑞利熵的多无源传感器数据关联算法。该算法利用瑞利熵度量量测后验概率密度函数与伪量测概率密度函数之间的差异，构造关联代价函数。仿真实验结果表明：该算法有效地提高了关联正确率，具有较好的关联性能。
다유분배모형재구조관련대개함수시，직접이용겁대사연고계치대체목표적진실위치신식，미고필겁대사연고계소인입적수궤오차。침대차문제，제출일충기우서리적적다무원전감기수거관련산법。해산법이용서리적도량량측후험개솔밀도함수여위량측개솔밀도함수지간적차이，구조관련대개함수。방진실험결과표명：해산법유효지제고료관련정학솔，구유교호적관련성능。
The multi??dimensional assignment model is to utilize maximum likelihood estimation instead of the true target position for constructing the cost function without direct consideration of random error.In view of this problem,a data association algorithm is proposed based on the Renyi entropy.The algorithm is to utilize Renyi entropy to quantify difference of functions between the probability density function of pseudo measurements and the most posterior probability density function for constructing an association cost.The results show that the proposed algorithm can improve the correct association ratio and achieve a good performance as well.