首页 | 本学科首页   官方微博 | 高级检索  
     

基于SVM-UPF的雷达弱小目标检测前跟踪算法
引用本文:秦占师,张智军,曹晓英,陈稳. 基于SVM-UPF的雷达弱小目标检测前跟踪算法[J]. 火力与指挥控制, 2016, 0(3): 48-52. DOI: 10.3969/j.issn.1002-0640.2016.03.013
作者姓名:秦占师  张智军  曹晓英  陈稳
作者单位:空军工程大学航空航天工程学院,西安,710038
基金项目:陕西省电子信息系统综合集成重点实验室基金资助项目(201107Y03)
摘    要:针对低信噪比条件下雷达弱小目标的检测与跟踪,提出了基于支持向量机和无迹粒子滤波的检测前跟踪算法。该算法采用无迹卡尔曼滤波生成粒子滤波的重要性密度函数,提高了粒子的使用效率,在此基础上将支持向量机引入到粒子重采样步骤中,通过构建状态的后验概率密度函数来获得多样性的新粒子,有效解决了粒子贫化问题,仿真结果表明,该算法提高了目标的检测概率和跟踪精度。

关 键 词:检测前跟踪  粒子滤波  无迹卡尔曼滤波  支持向量机

Track-before-Detect Algorithm for Radar Weak Target Based on Support Vector Machines Unscented Particle Filter
Abstract:An improved Track-Before-Detect (TBD)algorithm based on support vector machines and unscented particle filter is proposed for weak target detection and tracking in low Signal to Noise Radio (SNR)environment. The improved algorithm uses the Unscented Kalman filter to generate the important proposal distribution which can match the true posterior distribution more closely. On this basis,the article introduces support vector machines into particle resampling. By building the posterior probability density model of the states,diversiform particles can be gained. And the impoverishment problem is solved effectively by these diversiform particles. The simulation results show that the improved algorithm can improve probability of detection and tracking accuracy.
Keywords:track-before-detect  particle filter  unscented Kalman filter  support vector machines
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号