|本期目录/Table of Contents|

[1]陈未未,张兴敢*.基于一维距离像和微动特征的弹道导弹识别方法[J].南京大学学报(自然科学),2016,52(6):1113.[doi:10.13232/j.cnki.jnju.2016.06.015]
 Chen Weiwei,Zhang Xinggan*.A recognition method of ballistic missile based on multiple feature combination[J].Journal of Nanjing University(Natural Sciences),2016,52(6):1113.[doi:10.13232/j.cnki.jnju.2016.06.015]
点击复制

基于一维距离像和微动特征的弹道导弹识别方法
()
     

《南京大学学报(自然科学)》[ISSN:0469-5097/CN:32-1169/N]

卷:
52
期数:
2016年第6期
页码:
1113
栏目:
出版日期:
2016-12-01

文章信息/Info

Title:
A recognition method of ballistic missile based on multiple feature combination
作者:
 陈未未张兴敢*
南京大学电子科学与工程学院,南京,210023
Author(s):
 Chen WeiweiZhang Xinggan*
School of Electronic Science and Engineering,Nanjing University,Nanjing,210023,China
关键词:
 目标识别多特征联合高分辨一维距离像微动特征支持向量机
Keywords:
 target recognitionmultiple feature combinationHRRPmicro­motion featureSVM
分类号:
TP181
DOI:
10.13232/j.cnki.jnju.2016.06.015
文献标志码:
A
摘要:
弹道导弹目标识别是导弹防御系统的重要环节.用于弹道导弹识别的特征通常包括RCS特征、极化特征、雷达高分辨一维距离像(HRRP)、ISAR像、微动特征等.研究目标散射中心模型,给出了基于散射中心理论的HRRP特征.弹道导弹在释放诱饵过程中,弹头和诱饵在结构和质量上的差别会表现在微运动特征上,据此构建了弹头及诱饵的微运动模型,得到弹头进动模型及诱饵摆动模型,对所建模型回波进行短时傅里叶变换(STFT),提取时频脊得到微动特征.弹头及其诱饵有着丰富的结构信息,仅依靠单一特征识别弹头目标效果并不理想.提出综合HRRP特征与微动特征的多特征联合识别方法,对联合的多特征采用主成分分析(PCA)降维,采用支持向量机(SVM)作为分类算法,仿真结果表明,联合HRRP特征与微动特征并通过PCA降维后弹头识别率得到明显提升.
Abstract:
The purpose of this paper is to increase the recognition rate of projectile target.For identifying projectile target,it is necessary to extract target feature.Ballistic missile features commonly used in the scientific research work include radar cross section(RCS)feature,polarization feature,high resolution range profile(HRRP),inverse synthetic aperture radar(ISAR)image,micro­motion feature etc.This paper mainly elaborates HRRP and micro­motion feature.In order to simplify the calculation of HRRP,we apply target scattering centers model.Ballistic missile release the decoy to avoid interception during the flight,causing warhead’s motion behaves as procession while decoy’s motion behaves as swaying.This study analyses how warhead and decoy moves when ballistic missile release the decoy and builds models for them.We process micro­motion model with short­time Fourier transform and extract the time­frequency ridge as micro­motion feature.Warhead and decoy are abundant in structure information so it is not proper to identify projectile target merely rely on one single feature.This paper puts forward a superior recognition method based on multiple feature combination,combining HRRP feature with micro­motion feature.We use principal component analysis(PCA)to reduce the dimensionality and choose support vector machine(SVM)as classification algorithm.We draw HRRP figure and multiple feature spectrum figure for the warhead and the decoy through the simulation experiment.In order to simulate the target recognition process accurately,this paper change the number of test set and create a table of comparing results.Simulation experiment shows that the recognition rate of projectile target significantly improved compared to recognition relying on one single feature.

参考文献/References:

[1] Liu H,Chen F,Du L,et al.Robust radar automatic target recognition algorithm based on HRRP signature.Frontiers of Electrical and Electronic Engineering,2012,7(1):49-55.
[2]  Dong W G,Li Y J.Radar target recognition based on micro­doppler effect.Optoelectronics Letters,2008,4(6):456-459.
[3]  Chen V C,Li F,Ho S,et al.Micro­doppler effect in radar:phenomenon,model,and simulation study.IEEE Transactions on Aerospace & Electronic Systems,2006,42:2-21.
[4]  金光虎,高勋章,黎 湘等.基于ISAR像序列的弹道目标进动特征提取.电子学报,2010,38(6):1233-1238.(Jin G H,Gao X Z,Li X.Precession feature extraction of ballistic targets based on dynamic isar image sequence.Chinese Journal of Electronics,2010,38(6):1233-1238.)
[5]  苏东林,曾国奇,刘 焱等.运动目标RCS特性分析.北京航空航天大学学报,2006,12(12):1413-1417.(Su D L,Zeng G Q,Liu Y,et al.RCS study of moving radar targets.Journal of Beijing University of Aeronautics and Astronautics,2006,32(12):1413-1417.)
[6]  戴 军,方 晖,张兴敢.基于RCS的弹道导弹中段目标联合识别研究.南京大学学报(自然科学),2015,51(1):20-24.(Dai J,Fang H,Zhang X G.Simulation of RCS of ballistic missile warhead.Journal of Nanjing University(Natural Sciences),2015,51(1):20-24.)
[7]  程 旭,马 梁,李永祯等.弹道目标极化特征可分性研究.雷达科学与技术,2011,5(5):457-463.(Cheng X,Ma L,Li Y Z.Research on the separability of ballistic targets’polarimetry characteristics.Radar Science and Technology,2011,5(5):457-463.)
[8]  关永胜,左群声,刘宏伟.基于微多普勒特征的空间锥体目标识别.电波科学学报,2011,26(2):209-215.(Guan Y S,Zuo Q S,Liu H W.Cone­shaped target recognition in exo­atmosphere based on micro­doppler signature.Chinese Journal of Radio Science,2011,26(2):209-215.)
[9]  陈 凤,杜 兰,刘宏伟等.一种利用强度信息的雷达HRRP自动目标识别方法.电子学报,2009,37(3):459-463.(Chen F,Du L,Liu H W.Radar HRRP automatic target recognition using amplitude information.Chinese Journal of Electronics,2009,37(3):459-463.)
[10]  金 盛,高梅国,王 洋.基于RCS的空间目标识别技术.现代雷达,2010,32(6):59-62.(Jin S,Gao M G,Wang Y.Technology of space target recognition based on RCS.Modern Radar,2010,32(6):59-62.)
[11]  Decoste D,Schölkopf B.Training invariant support vector machines.Machine Learning,2002,46(1-3):161-190.
[12]  Yang X W,Lin D,Hao Z F,et al.A fast SVM training algorithm based on the set segmentation and k­means clustering.Progress in Natural Science,2003,10(10):750-755.
[13]  Yang J,Zhang D,Frangi A F,et al.Two­dimensional PCA:A new approach to appearance­based face representation and recognition.IEEE Transactions on Pattern Analysis & Machine Intelligence,2004,26(1):131-137.
[14]  张利军,刘兴霞.基于散射中心理论的雷达回波一维距离像模拟研究.克拉玛依学刊,2010,347-348.(Zhang L J,Liu X X.Research on radar­echo HRRP based on scattering centers theory.Journal of Karamay,2010:347-348.)
[15]  王 见,李金同,卢华玲等.采用STFT­Wigner变换抑制Wigner­Ville分布交叉项.重庆大学学报,2013,36(8):15-18.(Wang J,Li J T,Lu H L.Using STFT­Wigner transform to suppress the cross terms in Wigner­Ville distribution.Journal of Chongqing University,2013,26(8):15-18.)
[16]  王兆云,张兴敢,柏业超.基于微多普勒的锥体目标进动和结构参数估计.南京大学学报(自然科学),2014,50(2):148-153.(Wang Z Y,Zhang X G,Bai Y C.Precession and structural parameter estimation of cone­shaped target based on the micro­Doppler.Journal of Nanjing University(Natural Sciences),2014,50(2):148-153.)

相似文献/References:

备注/Memo

备注/Memo:
基金项目:江苏省基础研究计划(BK20151391)
收稿日期:2016-03-09
*通讯联系人,E­mail:zhxg@nju.edu.cn
更新日期/Last Update: 2016-11-21