机动目标自适应高斯模型与跟踪算法

提出了一种描述机动目标运动状态的自适应高斯模型,在这种模型中,机动目标的加速度被认为是具有非零均值、时间相关的随机过程,并假定其概率密度函数服从高斯分布。指出了机动目标运动模型的均值和方差与目标机动加速度最佳当前估计值之间的关系,在此基础上,提出了相应的自适应卡尔曼滤波算法。仿真结果表明,该算法对机动目标在不同机动方式下的位置、速度和加速度均有良好的跟踪效果,且所需计算量小。

An Adaptive Gauss Model and Tracking Algorithm for Maneuvering Target

In this paper, a new model and a tracking algorithm for maneuvering target are proposed. In this model, the acceleration of a maneuvering target is considered as a time-correlation random process with non-zero mean values and the probability density function of the acceleration is assumed Gaussian probability density function. The mean value of the function is the optimal estimation of the target acceleration at present and its variance is directly proportional to the square of the difference of the optimal estimations of the target acceleration at present. When any prior knowledge about the maneuver cannot be obtained, this model may describe the statistical characteristics of an unknown maneuver well.Based on the model, an acceleration adaptive Kalman filtering algorithm is presented and some Monte Carlo simulation results are given in this paper. The simulation results show that the model and adaptive algorithm proposed in this paper can well estimate the position, velocity and acceleration of target and requires less computation, no matter the target is maneuvering at any way.