快速JPDA算法的递归和并行实现

联合概率数据关联算法（ＪｏｉｎｔＰｒｏｂａｂｉｌｉｓｔｉｃＤａｔａＡｓｏｃｉａｔｉｏｎ，ＪＰＤＡ）是密集杂波环境下一种良好的多目标数据关联跟踪算法。但是，当目标的数目增大时，关联概率计算时的计算量爆炸效应一直是一个难题。为降低计算量，有不少文献讨论了次优ＪＰＤＡ算法，但都是以降低关联跟踪性能为代价的。本文将从联合关联事件的构造出发，讨论关联假设事件的分层构造以达到降低计算量的目的。这里的层次可从０取值到某一Ｌ值，０层表示没有任何目标能够跟当前的观测数据关联。Ｌ层表示共有Ｌ个目标可以跟当前扫描得到的观测数据相关联。本文在关联事件的构造中，各层次的搜索具有递归性并可以独立进行，因而可以并行实现。文中还将本文的方法跟有关文献作了比较，并且给出相应的计算机仿真实验及其结果

Recursive and Parallel Implementation of Fast JPDA Algorithm

The joint probabilistic data association (JPDA)is a very fine optimal multitarget tracking and associating algorithm in clutter. However, the calculation explosion effect on computation of association probabilities has been a difficulty. To reduce the calculation load, many papers have discussed near optimal algorithms which are in the cost of reduction the performance of association. This paper will present a method to reduce the calculation load by means of layered searching construction of the association hypothesis events. The layer here can take an integer value from 0 to l. Layer 0 means that no target can find its association data from current returns. And Layer l means that l targets can find their association data. Our layered construction method in the paper is recursive with independence among layers, so it can also be implemented in aparallel structure. Comparative analysis of the method with relative methods in other references and the corresponding computer simulation tests and its results are also given in the paper.