汽车雷达多目标跟踪的模糊数据关联

介绍了一种量测(新测目标)到目标(已知目标)之间的模糊数据关联方法，将模糊聚类均值方法和决策逻辑方法相结合，利用Mahalanobis距离代替聚类运算中的欧氏距离，使量测与目标预测值之间的相似性度量更准确，应用决策逻辑确定量测与目标预测值的关联关系。仿真表明这种方法简单，在杂波环境下，有较高的跟踪精度，这种方法可以用于道路条件下，基于汽车雷达的多目标的可靠跟踪。

Fuzzy Data Association in Automotive Radar Multi-target Tracking

A method of fuzzy data association between the measurement and the p rediction of object is proposed in this paper, based on the combination of fuzzy clustering means algorithm and decision logic algorithm. The Euclidean distance measure is replaced with Mahalanobis distance measure in fuzzy clustering means algorithm, making the similarity between the measurement and the prediction mor e accurate, and the decision logic algorithm is used for determining the associa tion relation. Simulation results show that the proposed method is simple, and i ts tracking accuracy in heavily cluttered condition is high. The method can be u sed for tracking multi target on road with automotive radar.