基于线性动态模型的雷达高分辨距离像小样本目标识别方法

王鹏辉; 刘宏伟; 杜兰; 潘勉; 张学峰

doi:10.3724/SP.J.1146.2011.00680

基于线性动态模型的雷达高分辨距离像小样本目标识别方法

doi: 10.3724/SP.J.1146.2011.00680

基金项目:

国家自然科学基金(60901067, 61001212)，新世纪优秀人才支持计划项目(NCET-09-0630)，长江学者和创新团队发展计划项目(IRT0954)和中央高校基本科研业务费专项资金联合资助课题

计量
- 文章访问数: 2986
- HTML全文浏览量: 106
- PDF下载量: 736
- 被引次数: 0
出版历程
- 收稿日期: 2011-07-03
- 修回日期: 2011-11-17
- 刊出日期: 2012-02-19

Linear Dynamic Model Based Radar HRRP Target Recognition under Small Training Set Conditions

摘要

摘要: 为了解决雷达高分辨距离像识别系统对训练样本需求量过大的问题，该文提出一种基于线性动态模型的小样本目标识别方法。首先分析了距离像频谱的统计特性，然后从其广义平稳性出发，使用线性动态模型对距离像频谱幅度建模，并用期望最大化算法估计模型参数。实测数据的实验结果表明：即使在很少的训练样本条件下，该方法仍能获得较高的正确识别率和良好的拒判性能。
- 雷达目标识别 /
- 高分辨距离像 /
- 广义平稳-不相关散射 /
- 线性动态模型
Abstract: To relax the heavy requirement of training sample size in the radar High Resolution Range Profile (HRRP) target recognition, a linear dynamic model based recognition method is proposed. Firstly, the statistical characteristic of HRRPs frequency spectrum is analyzed and considered to be a Wide Sense Stationary (WSS) process. Then a linear dynamic model is employed to model the amplitude of frequency spectrum and an Expectation Maximization (EM) algorithm is adopted to estimate the model parameters. Finally, experimental results based on measured data show that the proposed method can obtain satisfactory recognition accuracy and rejection performance even with a very few training samples.
- Radar target recognition /
- High Resolution Range Profile (HRRP) /
- Wide Sense Stationary- Uncorrelated Scattering (WSS-US) /
- Linear dynamic model

HTML全文

参考文献(1)

朱劼昊, 周建江, 吴杰. 基于半参数化概率密度估计的雷达目标识别[J]. 电子与信息学报, 2010, 32(9): 2161-2166. Zhu Jie-hao, Zhou Jian-jiang, and Wu Jie. Radar target recognition based on semi-parametric density estimation[J]. Journal of Electronics Information Technology, 2010, 32(9): 2161-2166. [2] Du L, Wang P, and Liu H, et al.. Bayesian spatiotemporal multitask learning for radar HRRP target recognition[J]. IEEE Transactions on Signal Processing, 2011, 59(7): 3182-3196.[3] Shi L, Wang P, and Liu H, et al.. Radar HRRP statistical recognition with local factor analysis by automatic Bayesian Ying-Yang harmony learning[J]. IEEE Transactions on Signal Processing, 2011, 59(2): 610-617.[4] Duda R O, Hart P E, and Stork D G. Pattern Classification[M]. New York: John Willy and Sons, Inc, 2001: 172-174.[5] Jacobs S P and OSullivan J A. Automatic target recognition using sequences of high resolution radar range profiles[J]. IEEE Transactions on Aerospace Electronic Systems, 2000, 36(2): 364-380.[6] Du L, Liu H, and Bao Z. Radar HRRP statistical recognition: parametric model and model selection[J]. IEEE Transactions on Signal Processing, 2008, 56(5): 1931-1944.[7] Zyweck A and Bogner R E. Radar target classification of commercial aircraft[J]. IEEE Transactions on Aerospace Electronic Systems, 1996, 32(2): 598-606.[8] Pei B and Bao Z. Multi-aspect radar target recognition method based on scattering centers and HMMs classifiers[J]. IEEE Transactions on Aerospace Electronic Systems, 2005, 41(3): 1067-1074. [9] Wong S K. Non-cooperative target recognition in the frequency domain[J]. IEE Proceedings Radar, Sonar Navigation, 2004, 151(2): 77-84.[10] Guo Zun-hua and Li Shao-hong. One-dimensional frequency- domain feature for aircraft recognition from radar range profiles[J]. IEEE Transactions on Aerospace Electronic Systems, 2010, 46(4): 1880-1892.[11] Wang P, Dai F, and Pan M, et al.. Radar HRRP target recognition in frequency domain based on autoregressive model[C]. IEEE Radar Conference, Kansas City, USA, 2011: 714-717.[12] Van Trees H L. Detection, Estimation, and Modulation Theory, Part III[M]. New York: John Willy and Sons, Inc, 2001: 415-419.[13] Digalakis V, Rohlicek J, and Ostendorf M. ML estimation of a stochastic linear system with the EM algorithm and its application to speech recognition[J]. IEEE Transactions on Speech Audio Processing, 1993, 1(4): 431-442.[14] Shumway R H and Stoffer D S. An approach to time series smoothing and forecasting using the EM algorithm[J]. Journal of Time Series Analysis, 1982, 3(4): 253-264.

施引文献

资源附件(0)

访问统计