基于最大似然估计的不可区分多目标定位法

Location method for indistinguishable multi-target based on maximum likelihood estimation

传统的最大似然估计定位法无法剔除误差较大或错误的参数,且不适用于多目标情形。结合最大似然估计理论,针对不可区分多目标定位问题,引出了目标位置信息场定位法,通过加入代价函数使得该方法能够剔除错误数据,降低误差大的数据对定位结果估计的影响。仿真结果表明,目标位置信息场定位法具有筛选有用参数信息的能力,且适用于不可区分的多目标定位,能够同时确定目标数目和位置,验证了方法的有效性。

The traditional maximum likelihood estimation method can＇t eliminate error or wrong parameter,and does not apply to multi-target situation. This paper deduced position information field location method for target for multi-target location problem combined with maximum likelihood estimation theory. This method could eliminate wrong data and reduced the impact of the great error in the data to positioning results by adding the cost function. Simulation results show that the location method is deduced has the ability of screening useful parameters information,and is suitable for the indistinguishable multi-target localization,can simultaneously determine target number and position. The effectiveness of the method is verified.