Robust radar automatic target recognition algorithm based on HRRP signature 被引量：8

Robust radar automatic target recognition algorithm based on HRRP signature

导出

摘要 Automatic target recognition （ATR） is an important function for modern radar. High resolution range profile （HRRP） of target contains target struc- ture signatures, such as target size, scatterer distribu- tion, etc, which is a promising signature for ATR. Sta- tistical modeling of target HRRPs is the key stage for HRRP statistical recognition, including model selection and parameter estimation. For statistical recognition al- gorithms, it is generally assumed that the test samples follow the same distribution model as that of the train- ing data. Since the signal-to-noise ratio （SNR） of the received HRRP is a function of target distance, the as- sumption may be not met in practice. In this paper, we present a robust method for HRRP statistical recogni- tion when SNR of test HRRP is lower than that of train- ing samples. The noise is assumed independent Gaus- sian distributed, while HRRP is modeled by probabilistic principal component analysis （PPCA） model. Simulated experiments based on measured data show the effective- ness of the proposed method. Automatic target recognition （ATR） is an important function for modern radar. High resolution range profile （HRRP） of target contains target struc- ture signatures, such as target size, scatterer distribu- tion, etc, which is a promising signature for ATR. Sta- tistical modeling of target HRRPs is the key stage for HRRP statistical recognition, including model selection and parameter estimation. For statistical recognition al- gorithms, it is generally assumed that the test samples follow the same distribution model as that of the train- ing data. Since the signal-to-noise ratio （SNR） of the received HRRP is a function of target distance, the as- sumption may be not met in practice. In this paper, we present a robust method for HRRP statistical recogni- tion when SNR of test HRRP is lower than that of train- ing samples. The noise is assumed independent Gaus- sian distributed, while HRRP is modeled by probabilistic principal component analysis （PPCA） model. Simulated experiments based on measured data show the effective- ness of the proposed method.

作者 Hongwei LIU Feng CHEN Lan DU Zheng BAO

机构地区 National Laboratory of Radar Signal Processing

出处《Frontiers of Electrical and Electronic Engineering in China》 CSCD 2012年第1期49-55,共7页 中国电气与电子工程前沿（英文版）

关键词 radar target recognition high resolution range profile （HRRP） probabilistic principal component analysis （PPCA） radar target recognition, high resolution range profile （HRRP）, probabilistic principal component analysis （PPCA）

分类号 TP391.41 [自动化与计算机技术—计算机应用技术] TN957.3 [电子电信—信号与信息处理]

引文网络
相关文献

参考文献10

1Webb A R. Gamma mixture models for target recognition[J].Pattern Recognition,2000,(12):2045-2054.
2Copsey K,Webb A R. Bayesian Gamma mixture model approach to radar target recognition[J].IEEE Transactions on Aerospace and Electronic Systems,2003,(04):1201-1217.doi:10.1109/TAES.2003.1261122.
3Du L,Liu H W,Bao Z,Zhang J Y. A two-distribution compounded statistical model for radar HRRP target recognition[J].IEEE Transactions on Signal Processing,2006,(06):2226-2238.doi:10.1109/TSP.2006.873534.
4Du L,Liu H W,Bao Z. Radar HRRP statistical recognition based on hypersphere model[J].Signal Processing,2008,(05):1176-1190.doi:10.1016/j.sigpro.2007.11.003.
5Du L,Liu H W,Bao Z. Radar HRRP statistical recognition:Parametric model and model selection[J].IEEE Transactions on Signal Processing,2008,(05):1931-1944.doi:10.1109/TSP.2007.912283.
6Shi L,Wang P H,Liu H W,Xu L Bao Z. Radar HRRP statistical recognition with local factor analysis by automatic Bayesian Ying-Yang harmony learning[J].IEEE Transactions on Signal Processing,2011,(02):610-617.
7Wang P H,Shi L,Du L,Liu H W Xu L Bao Z. Radar HRRP statistical recognition with temporal factor analysis by automatic Bayesian Ying-Yang harmony learning[J].Frontiers of Electrical and Electronic Engineering in China,2011,(02):300-317.doi:10.1007/s11460-011-0149-8.
8Xu L,Krzyzak A,Oja E. Rival penalized competitive learning for clustering analysis,RBF net,and curve detection[J].IEEE Transactions on Neural Networks,1993,(04):636-649.
9Xu L. Bayesian Ying-Yang system,best harmony learning and five action circling[J].Frontiers of Electrical and Electronic Engineering in China,2010,(03):281-328.
10Xn L. Bayesian Ying-Yang system and theory as a unified statistical learning approach: (Ⅴ) Temporal modeling for temporal perception and control.Invited Paper[A].1998.877-884.