论文部分内容阅读
对概率数据关联（ＰＤＡ）滤波器进行了杂波中跟踪的自适应检测门限最佳化的研究。这个问题［４］的更早些研究包括一种近似稳态的状态误差协方差的分析，而且只适用于非时变系统。此外，这种方法需要许多有关误差协方差校正方程的假设和近似值，并采用一种很麻烦的最佳化图解算法。在本文中我们提出了两种自适应门限最佳化方案，即先延和后延最佳化算法，这两种算法使检测门限上的均方状态估值误差最小，检测门限取决于分别至以前和现行时间步长的数据。这些算法适用于时变系统中的实时实现。本文还介绍一些模拟结果
Research on adaptive threshold detection for clutter in probabilistic data association (PDA) filter. Earlier studies of this problem [4] included an analysis of covariance of state errors of approximately steady state, and applied only to time-invariant systems. In addition, this method requires a lot of assumptions and approximations about the error covariance correction equations and uses a cumbersome optimization graphing algorithm. In this paper, we propose two kinds of adaptive threshold optimization schemes, that is, the first delay and the late delay optimization algorithm, which minimize the mean square state estimation error on the detection threshold, the detection threshold depends on Previous and current time step data. These algorithms are suitable for real-time implementation in time-varying systems. This article also describes some of the simulation results