基于D-S证据理论的阵群目标数据关联算法

由于星载传感器获取数据的时间间隔较长，对监视区域中的每个目标进行稳定有效的跟踪是非常困难的。为此，该文将阵群目标作为研究对象，充分利用阵群目标相对稳定的编成、队形特征，提出了一种基于D-S证据理论的阵群目标数据关联算法。首先，建立阵群目标的编成特征和队形特征的描述模型，并据此提取阵群目标的编成及队形特征；其次，通过D-S证据理论，分别利用编成和队形特征建立阵群目标的关联匹配模型，计算相应的基本概率分配函数；最后，对基于编成和队形特征关联的基本概率分配函数进行证据合成，建立综合的基本概率分配函数，并采用二维分配方法实施关联判决，得出关联结果。仿真实验证实了该算法的有效性。 

A Group Target Data Association Algorithm Based On D-S evidence theory

It is difficult to track every target steadily and effectively when the interval of obtaining data from the spaceborne sensor is relatively long. Consequently, a scheme is developed which regards the group targets as the study object and this paper presents a group target data association algorithm based on D-S evidence theory that takes full advantage of their relatively stable composition and array features. Firstly, the composition feature and the array feature of group targets are extracted based on their mathematics model which is established. Secondly, the association matching model of group targets is established that makes use of the composition features and the array features. The basic probability assignment function of the composition features and the array features are calculated respectively based on D-S evidence theory. And finally, the synthetical basic probability assignment function is established after the two basic probability assignment functions are synthesized based on D-S evidence theory and the association result is obtained after making use of the 2D assignment algorithm. The simulation has proved the effectiveness of the algorithm.