雷达高分辨距离像分类器的参数自适应学习算法

袁莉; 刘宏伟; 保铮

doi:10.3724/SP.J.1146.2006.00879

雷达高分辨距离像分类器的参数自适应学习算法

doi: 10.3724/SP.J.1146.2006.00879

基金项目:

国家自然科学基金(60302009)资助课题

计量
- 文章访问数: 3257
- HTML全文浏览量: 85
- PDF下载量: 877
- 被引次数: 0
出版历程
- 收稿日期: 2006-06-19
- 修回日期: 2006-11-27
- 刊出日期: 2008-01-19

Adaptive Learning of Classifier Parameters for Radar High Range Resolution Profiles Recognition

摘要

摘要: 雷达高分辨率距离像具有目标姿态敏感性的特点，在识别时的一种解决方法是对目标不同角域建立不同的统计模型。在给定系统参数条件下，选择目标划分角域个数及每个角域覆盖范围是影响识别器运算量及识别性能的关键。该文给出了一种基于数据的自适应学习上述分类器参数的算法，基于联合高斯分布的数据模型通过迭代算法来确定数据划分边界，并自动确定目标角域个数。与等间隔数据划分方法相比，本文方法在降低识别运算量的同时，可以提高识别性能。基于实测数据的实验结果表明该方法是有效的。
- 雷达自动目标识别; 高分辨距离像; 自适应高斯分类器
Abstract: Radar High Range Resolution Profile (HRRP) is very sensitive to target aspect variation. To deal with this problem, usually, multiple statistical models are built for different target aspect sector when using HRRP for target recognition. Therefore, how to determine target aspect sector number and how to divide target aspect sector play an important role in classifier training. A data driven adaptive learning algorithm is proposed in this paper, which determines the target aspect sector boundary based on a multivariate Gaussian statistical data model and an iteration algorithm, and the target aspect sector number can be determined simultaneously. Comparing with the traditional equal interval target aspect partition approach, the proposed approach can achieve better recognition performance with lower computation complexity. Experimental results based on the measured data show the efficiency of the proposed method.

HTML全文

参考文献(1)

Hudson S and Psaltis D. Correlation filters for aircraft identification from radar range profile. IEEE Trans. on AES, 1993, 29(3): 741-748.[2]Li H J and Yang S H. Using range profiles as feature vectors to identify aerospace objects. IEEE Trans. on AP, 1993, 41(3): 261-268.[3]Jacobs S P and Osollivan J A. Automatic target recognition using sequences of high resolution radar-profiles. IEEE Trans. on AES, 2000, 36(2): 364-380.[4]Xing M D, Bao Z, and Pei B N.The properties of high- resolution range profiles[J].Optical Engineering.2002, 41(2):493-504[5]刘宏伟, 杜兰, 袁莉, 保铮. 雷达高分辨距离像目标识别研究进展.电子与信息学报, 2005, 27(8), 1328-1334.[6]Liu Hong-wei, Du Lan, Yuan Li, and Bao Zhen. Progress in radar automatic target recongnition based on high range resolution profile[J].Journal Electronics Information Technology.2005, 27(8):1328-1334[7]Du L, Liu H W, and Bao Z, et al.. A two-distribution compounded statistical model for radar HRRP target recognition[J].IEEE Trans. on SP.2006, 54(6):2226-2238[8]Steinberg B D. Microwave Imaging with Large Antenna Arrays: Radio Camera Principle and Technique [M]. New York: John Wiley and Sons, 1983: 25-223.[9]Webb A R. Gamma mixture models for target recognition[J].Pattern Recognition.2000, 33(12):2045-2054[10]Copsey K and Webb A R. Bayesian gamma mixture model approach to radar target recognition, IEEE Trans. on AES, 2003, 39(4): 1201-1217.[11]杜兰, 刘宏伟, 保铮. 利用目标方位信息改善雷达距离像识别性能. 系统工程与电子技术, 2004.26(8): 1040-1043.[12]Li Q, and Iiavarasan P, et al.. Radar target identification using a combined early-time/late-time e-pulse technique. IEEE Trans. on AP, 1998, 46(9): 1272-1278.[13]Williams R and Westerkamp J. Automatic target recognition of time critical moving targets using 1D high range resolution (HRR) radar. IEEE AES Magazine, 2000, 15(4): 37-43.

施引文献

资源附件(0)

访问统计