基于“当前”统计模型的机动目标自适应跟踪算法  

Adaptive Tracking Algorithm for Maneuvering Targets Based on Current Statistical Model

作　　者：徐洋[1] 徐松涛[1] 赵建恒[1] 杨涛[1] 

机构地区：[1]空军工程大学航空航天工程学院,陕西西安710038

出　　处：《现代防御技术》2014年第5期121-126,共6页Modern Defence Technology

基　　金：陕西省电子信息系统综合集成重点实验室基金(201107Y03)

摘　　要：针对"当前"统计模型对加速度极值及机动频率需人为设定的缺陷,提出了一种基于滤波残差的高斯型隶属度函数改进算法,该法在跟踪过程中对加速度极值进行自适应调整。引入一种基于残差的Sigmoid二次型隶属度函数,通过自适应改变机动频率,使模型趋于目标真实状态。理论分析和仿真结果表明,改进的模型避免了人为引入误差,提高了机动目标的跟踪精度,算法简单,易于工程实现。The current statistical model has the weakness of excessive reliance of limit acceleration and maneuvering frequency. Aiming at this issue, an improved algorithm based on the filtering residuals＇ Gaussian membership function is utilized. It can adaptively control the limit acceleration while tracking the target. A Sigmoid quadratic membership function is introduced based on the filtering residuals, and it makes the proposed model match the target real state closer by adjusting the maneuvering frequency. The- oretical analysis and simulation results show that the improved model avoids the human error and improves the tracking accuracy. The algorithm is easy and good for project implementation.

关 键 词：“当前”统计模型 滤波残差 高斯隶属度函数 Sigmoid隶属度函数 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TP301.6[自动化与计算机技术—控制科学与工程]