论文部分内容阅读
在被动系统中,多传感器多目标数据关联一直是一个难解决的问题。对静态数据关联多维指派“组合爆炸”问题,许多外学者提出了像最小距离法、最大似然算法等多种解决方法,但它们或正确相关率较低,或计算量较大。基于上述问题,提出了一种基于运动目标在时间上具有连续性的先验知识的新的航迹关联算法,该算法根据数据列之间发展态势的相似或相异程度来衡量航迹间接近的程度,使航迹关联问题突破了样本容量和典型分布这两条限制。仿真结果表明该算法计算量小,正确关联率高,具有较高的工程应用价值。
In passive systems, multi-sensor multi-target data association has always been a difficult problem. Concerning the multidimensional assignment of static data “combinatorial explosion ”, many foreign scholars have put forward many solutions such as minimum distance method and maximum likelihood algorithm, but they have a lower correct correlation rate or a higher computational complexity. Based on the above problems, this paper proposes a new trajectory association algorithm based on the priori knowledge of the moving objects in time. This algorithm measures the distance between the tracks according to the similarity or dissimilarity of the development trend among the data columns The extent of the track association problem exceeded the sample size and the typical distribution of these two restrictions. The simulation results show that this algorithm has a small amount of computation, a high correct relevance rate and a high engineering application value.