多传感器广义概率数据关联算法研究

随着跟踪环境、跟踪对象的不断变化与发展,目标与量测已经很难用一一对应的关系去描述;广义数据关联算法（GPDA）提出目标与量测多多对应的可行性规则,其性能在目标与量测无论是否在一一对应的情况下,均优于传统的JPDA算法,并且计算量、存储量均远小于JPDA;考虑到GPDA的上述优点,将GPDA算法拓展到多传感器数据关联,提出了多传感器广义概率数据关联算法（MSGPDA）来处理多传感器数据关联问题;仿真表明,MSGPDA算法由于利用多传感器信息,性能得到明显提高。

Multi- Sensor Generalized Probability Data Association Algorithm

With the change and development of modem multi-target tracking system, it is very difficult to deal with data" association problems simply by using the feasible rule based on the hypothesis of the association of measurements with targets is one-to-one belonging to each other, which is commonly used in JPDA. General probability association algorithm (GPDA) considers that the association of measurements and targets is multiple-to-multiple. Whether the practical association is one-to-one or not, GPDA always gets the better performance than JPDA, while the much smaller computation burden. Because of the merits of GPDA, multiple sensors generalized probability data association algorithm (MSGPDA) is presented to deal with the multiple sensors data association problem.. Simulation results show that MSGPDA gets the better performance because of the usage of multiple sensors information.