一种基于模型概率修正的IMM目标跟踪算法  

An IMM maneuvering target tracking algorithm based on amended model probability

作　　者：周科[1] 朱敏[1] 蒲柳[1] 

机构地区：[1]四川大学计算机学院,成都610064

出　　处：《四川大学学报（自然科学版）》2012年第3期577-581,共5页Journal of Sichuan University(Natural Science Edition)

基　　金：国家自然科学基金(60572175)

摘　　要：在IMM算法的基础上,提出了一种新的机动目标跟踪FIMM算法.该算法使用中值滤波对IMM算法模型更新概率进行平滑,再对其利用模糊推理系统进行实时修正,将修正后的概率作为最后输出的权值,让有用模型概率增大,减少了模型之间的竞争,提高跟踪精度.仿真实验表明,提出的FIMM算法显著提高了IMM算法的跟踪性能.A new maneuvering targets tracking algorithm FIMM is presented based on the IMM algorithm.The algorithm smooth the updated probaility of the IMM algorithm by the median filter,and then use the fuzzy inference system for real-time amendment, the result of which is as the final output weights.The FIMM algorithm increases the probability of a useful model,decreases the competition between models,and improves the tracking accuracy.Simulation results show that the FIMM algorithm proposed in this article significantly inproves the tracking performance of IMM algorithm.

关 键 词：机动目标跟踪 IMM算法 中值滤波 模糊推理系统 FIMM算法 

分 类 号：TN953[电子电信—信号与信息处理]