基于模糊多传感器数据融合的目标跟踪系统

Study on Target Tracking System based on Fuzzy Multi-sensor Data Fusion

为了克服使用单个传感器的局限性,目标跟踪系统中引入了多传感器数据融合(MSDF)算法。MSDF能有效减小污染传感器测量量的噪声,又可排除估计过程中的无效测量量。它既能处理线性传感器的数据融合问题,又能处理含噪声的非线性传感器的数据融合问题。为了克服缺乏目标运动的前期信息的不足,目标跟踪系统中还运用了模糊运动学过程模型。因此,尽管缺乏有关目标运动及估计过程中所包含的传感器前期统计信息,该目标跟踪系统的性能却与基于已知目标精确过程模型的广义卡尔曼滤波器的目标跟踪系统相当。

Multi-sensor data fusion （MSDF） algorithm is introduced to the target tracking system in order to overcome limitations of the single sensor. The MSDF can reduce noise of sensor measurement and eliminate inactive measurement in the estimation process. The MSDF can process not only data fusion of the linear sensor, but also data fusion of nonlinear sensor with noise. Process model of fuzzy kinematics is also applied to the target tracking system in order to overcome insufficiency of preceding information of target motion. Performance of the target tracking system is equivalent to that of target tracking system with generalized Kalman filter based on precise process model of the known target.