基于模糊聚类的异类多传感器数据关联算法

针对异类传感器观测空间不一致的问题，提出了基于模糊聚类的异类多传感器数据关联算法．该算法首先通过在不同传感器的观测空间上建立多目标运动状态的投影，将多传感器多目标关联问题分解为多个单传感器多目标的关联问题，再对单传感器采用模糊聚类的方法求解关联概率，实现了在密集杂波环境中多目标的数据关联和精确跟踪．该算法降低了多传感器多目标跟踪的复杂性和计算量，有效地解决了异类多传感器可用公共信息少的问题．仿真结果表明，该算法的跟踪误差要小于传统的联合概率数据关联算法，且具有更优越的跟踪性能．

Heterogeneous Multi-Sensor Data Association Algorithm Based on Fuzzy Clustering

For the inconsistency problem of heterogeneous sensors' measurement spaces, a new data association (DA) algorithm based on fuzzy clustering algorithm is presented. Firstly, the multi-sensor multi-target problem is decomposed into the DA problems of several single sensor multi-target by means of projecting the target states into the measurement spaces of the multi-sensor. Then, the DA probability can be obtained depending on the fuzzy clustering algorithm, and therefore an accurate tracking for multi-targets in heavily cluttered environment can be implemented. The presented algorithm can reduce computing complexity and solve the common information-lacking problem of heterogeneous sensors efficiently. The simulation results show that the tracking error of proposed algorithm is less then the exiting joint probabilistic data association (JPDA) algorithm and it has better tracking behavior.