基于数据压缩的多传感器多假设算法

为解决集中式多传感器系统中多目标跟踪问题,提出了一种新的多传感器多目标算法.提出的算法首先应用经典分配规则对每个传感器送来的观测数据进行排列组合,然后对每个组合中各量测点进行概率加权以获得一个等效量测点,最后根据每个等效量测点产生的互联假设计算其互联概率并获得融合中心的状态估计.给出了该算法与已有集中式多传感器联合概率数据互联算法的仿真比较,仿真结果表明该算法的跟踪性能在探测概率降低的跟踪环境下表现得更为优越. 

Multisensor multipled hypothesis algorithm based on data compressing technic

In order to solve the problem of multitarget tracking in centralized multisensor situation,a new multisensor multitarget tracking algorithm was presented.At first,the algorithm permuted and combined the measurement from each sensor using the rule of generalized classical assignment algorithm.Then,all of measurements in each assignment were combined into one equivalent measurement according to their weight in the assignment.Finally,the association probability of each equivalent measurement was calculated,and then the state estimation in fusion center was obtained.Some typical simulations were used to compare the performance of the algorithm with the other centralized multisensor joint probabilistic data association(MSJPDA) method,and the results show that the performance of the algorithm here is better than that of the MSJPDA,especially under the environment of the detection probability decreasing.