论文:2016,Vol:34,Issue(6):1022-1027
引用本文:
李彬, 李辉, 黄伟斌. 基于PPCA修正模型的HRRP稳健识别方法[J]. 西北工业大学学报
Li Bin, Li Hui, Huang Weibin. Modified PPCA Methods for Radar HRRP Robust Recognition[J]. Northwestern polytechnical university

基于PPCA修正模型的HRRP稳健识别方法
李彬, 李辉, 黄伟斌
西北工业大学 电子信息学院, 陕西 西安 710129
摘要:
高信噪比情况下,利用概率主成分分析(PPCA,probabilistic principal component analysis)模型识别雷达高分辨距离像(HRRP,high resolution range profile)取得了较高的识别率。但在实际工作环境中,测试阶段获取的HRRP常为低信噪比样本,由此造成的模型失配问题极大影响了识别性能。为此文章利用不同噪声来源造成的模型失配先验信息,在模型空间针对不同信噪比的测试样本补偿PPCA模型参数,以达到稳健识别的目的。另一方面,利用2种方法通过直接估计测试样本的噪声功率省去最优化计算的步骤,避免了求解最优补偿参数时需要大量计算的问题,提高了识别效率。最后,利用最大后验概率确定目标所属类别,证明了2种方法在信噪比低于20 dB时的可行性。
关键词:    雷达目标识别    飞机目标探测    脉冲重复频率    高分辨距离像    概率主成分分析    模型修正   
Modified PPCA Methods for Radar HRRP Robust Recognition
Li Bin, Li Hui, Huang Weibin
School of Electronic and Information, Northwestern Polytechnical University, Xi'an 710129, China
Abstract:
In the condition of high signal-to-noise ratio(SNR), utilizing probabilistic principal component analysis(PPCA) model obtained high recognition rate in radar high resolution range profile (HRRP) recognition field. But in the actual working environment, HRRPs getting from the test phase usually have low SNR which will cause model mismatch problem influencing recognition rate. In order to get noise robust PPCA based methods, according to the prior mismatch information which are caused by different noise sources, the modified PPCA statistic parameters are computed to make up for the error of mismatch in model space. On the other hand, the two methods proposed in this paper directly estimate the increased noise power to avoid the step in solving optimization problem of modified parameters which greatly improve the calculation efficiency. Finally, in the simulation experiment applying the maximum a posteriori probability classifier to test the modified PPCA model, the results show the feasibility of these two methods below 20 dB SNR.
Key words:    radar target recognition    aircraft detection    pulse repetition rate    high resolution range profile    probabilistic principal component analysis    model modification   
收稿日期: 2016-09-01     修回日期:
DOI:
基金项目: 国家自然科学基金(61571364)与西北工业大学研究生创新创意种子基金(Z2016022)资助
通讯作者:     Email:
作者简介: 李彬(1986-),西北工业大学博士研究生,主要从事模式识别及雷达数据处理研究。
相关功能
PDF(1190KB) Free
打印本文
把本文推荐给朋友
作者相关文章
李彬  在本刊中的所有文章
李辉  在本刊中的所有文章
黄伟斌  在本刊中的所有文章

参考文献:
[1] 郭尊华,李达,张伯彦,等. 雷达高距离分辨率一维像目标识别[J]. 系统工程与电子技术,2013,35(1):53-60 Guo Zunhua, LI Da, Zhang Boyan, et al. Survey of Radar Target Recognition Using One-Dimensional High Range Resolution Profiles[J]. Systems Engineering and Electronics, 2013, 35(1):53-60(in Chinese)
[2] Liu H W, Du L, Wang P H, et al. Radar HRRP Automatic Target Recognition:Algorithm and Applications[C]//IEEE CIE International Conference on Radar, 2011:14-17
[3] Du L, Liu H W, Bao Z. Radar HRRP Statistical Recognition:Parametric Model and Model Selection[J]. IEEE Trans on Signal Process, 2008, 56(5):1931-1944
[4] 王鹏辉,杜兰,刘宏伟,等. 雷达高分辨距离像分帧新方法[J]. 西安电子科技大学学报,2011,38(6):22-29 Wang Penghui, Du Lan, Liu Hongwei, et al. New Frame Segmentation Method for Radar HRRPs[J]. Journal of Xidian University, 2011,38(6):22-29(in Chinese)
[5] Liu H W, Chen F, Du L, et al. Robust Radar Automatic Target Recognition Algorithm Based on HRRP Signature[J]. Frontiers of Electrical and Electronic Engineering, 2012,7(1):49-55
[6] Du L, Liu H W, Wang P H, et al. Noise Robust Radar HRRP Target Recognition Based on Multitask Factor Analysis with Small Training Data Size[J]. IEEE Trans on Signal Processing, 2012, 60(7):3546-3559
[7] Pan M, Du L, Wang P H, et al. Noise-Robust Modification Method for Gaussian-Based Models with Application to Radar HRRP Recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2013,10(3):558-562
[8] Hou Q Y, Chen F, Liu H W, et al. Adaptive Statistical Model for Radar HRRP Target Recognition[C]//IET Radar Conference, 2009
[9] Tipping M E, Bishop C M. Mixtures of Principal Component Analyzers[J]. Neural Compute, 1999, 11(2):443-482
[10] Gales M J F, Woodland P C. Mean and Variance Adaptation Within the MLLR Framework[J].Computer Speech & Language, 1996, 10(4):249-264
[11] Pei Z J, Tong Q Q, Wang L N, et al. A Median Filter Method for Image Noise Variance Estimation[C]//International Conference on Information Technology and Computer Science, 2010, 13-16
[12] 黄得双. 高分辨雷达智能信号处理技术[M]. 北京:机械工业出版社, 2001 Huang Deshuang. Intelligent Signal Processing Technique for High Resolution Radars[M]. Beijing, China Machine Press, 2001:19-31(in Chinese)
相关文献:
1.段沛沛, 李辉, 李彬.基于压缩感知稀疏分解的一维距离像目标识别[J]. 西北工业大学学报, 2016,34(2): 256-261
2.段沛沛, 李辉, 李琦.基于结构划分字典学习的雷达目标识别[J]. 西北工业大学学报, 2015,33(4): 672-676