雷达数据关联中动态加权模糊C-均值聚类算法研究

针对雷达本身及测量的运动目标淹没在大量的杂波中而导致所测数据的不准确问题,文中对雷达测量的大量目标数据进行卡尔曼滤波,以减少数据关联时的计算冗余量；并对模糊C-均值(C-Means)聚类算法进行改进,改进后的算法利用实时目标航迹斜率的变化率对传统的模糊C-Means聚类算法进行动态加权,从而使模糊C-Means聚类算法的目标函数最优化,优化后的目标函数确定的聚类中心更加逼近目标的实际值,从而保证数据关联的准确度,并减少了计算时间,提高算法的效率.仿真实验表明,将文中基于目标航迹斜率变化率动态加权的模糊C-Means聚类算法应用于曲线运动目标的数据关联中,与传统的模糊C-Means聚类算法相比,可以提高数据关联准确度和效率.

A Study on Dynamic Weighted C-Means Fuzzy Clustering Algorithm of Radar Data Association

Facing to the problem of the radar and its target is submerged in a lot of clutter, which leading a poor accuracy of the data association. Firstly, the Kalman was used to filter target measurements data, in order to reduce the data associated computing redundancy. Then an improved fuzzy clustering algorithm is proposed in this paper. In the algorithm, the dynamic fuzzy clustering algorithm weight was updated by the change rate of the slope of the target track of moving targets measured by radar real-time. So the objective function of fuzzy clustering algorithm was optimized to make sure the cluster center approximate to the actual value of the target as soon as possible. As a result, the accuracy was ensured and the efficiency was improved. The simulation results show that, compared with the traditional fuzzy clustering algorithm, when the improved algorithm was adopted to associate the data of curve moving target, it can improve the accuracy of the data association and reduce the computing time, which was based on the change rate of target tracks slope.