期刊文献+

基于距离像幅度信息和Boosting的目标识别研究 被引量:1

Radar target recognition based on HRRP's amplitude and boosting
下载PDF
导出
摘要 在基于高分辨雷达距离像的目标识别中,有研究者指出散射点的位置信息具有比幅度信息更好的鉴别能力。对此,将距离像各距离单元按照幅度大小进行重排,得到只保留散射点幅度信息而去除散射点位置信息的平移不变特征,它反映了目标的反射特性,并利用Boosting算法和支持矢量机(SVM)进行了分类试验。基于实测数据的仿真结果表明,散射点的幅度同样是一种重要的识别信息。 In the target recognition based on radar high resolution range profile(HRRP), some researchers consider the scatter point's location has a better discrimination power than amplitude does. A new shift-invariant feature is obtained by sorting the range profile according to scatter point's amplitude, it contains no location information and reflects the target's reflection property. The boosting algorithm and SVM are used as the classifiers, experiment results based on measured data testified the scatter point's amplitude information has a good discrimination power too.
出处 《系统工程与电子技术》 EI CSCD 北大核心 2007年第10期1628-1630,共3页 Systems Engineering and Electronics
关键词 雷达 信号处理 目标识别 BOOSTING算法 radar signal processing target recognition Boosting algorithm
  • 相关文献

参考文献7

  • 1Zhang X,Shi Y,Bao Z.A new feature vector using selected bispectra for signal classification with application in radar target recognition[J].IEEE Trans.on SP,2001,49(9):1875-1885.
  • 2Kim K T,Seo D K,Kim H T.Efficient radar target recognition using the music algorithm and invariant feature[J].IEEE Trans.on AP,2002,50(3):325-337.
  • 3Bing N P,Zheng B.Multi-aspect radar target recognition method based on scattering centers and HMMS classifiers[J].IEEE Trans.on AE,2005,41(3):1067-1074.
  • 4Xing M D,Bao Z,Pei B N.The properties of high-resolution range profiles[J].Optical Engineering,2002,41(2):493-504.
  • 5Kearns M,Valiant L.Cryptographic limitation on learning Boolean formulae and finite automata[J].Journal of the ACM,1994,41(1):67-95.
  • 6Ratsh G,Onoda T,Muller K R.Soft margins for AdaBoost[J].Machine Learning,2001,42(3):287-320.
  • 7Muller K R,Mika S,Ratsh G,et al.An introduction to kernel-based learning algorithms[J].IEEE Trans.on NN,2001,12(2):181-201.

同被引文献17

  • 1荣海娜,张葛祥,金炜东.系统辨识中支持向量机核函数及其参数的研究[J].系统仿真学报,2006,18(11):3204-3208. 被引量:79
  • 2高隽.人工神经网络原理及仿真实例[M].2版.北京:机械工业出版社,2010.
  • 3Josef S, Vladimir T. On improved estimator for interceptor guidance[C]//Proc, of the American Control Conference, 2002 :203 - 208.
  • 4Talole S E, Phadke S B. Nonlinear target estimation in homing guidance[C]// Proc. o f AIAA Navigation and Control Conference, 2002:3122 - 3130.
  • 5Vapnik V N. The nature of statistical learning theory [M]. New York: Springer Verlag, 1995.
  • 6Vapnik V N. Statistical learning theory[M]. New York: Wiley, 1998.
  • 7Vapnik V N, Golowich S. A smola support vector method for function approximation[C]//Proc, of the Neural Information Processing Systems, 1997 : 281 - 287.
  • 8Liu G P. Nonlinear identification and control : a neural network approach[M]. New York: Springer, 2001.
  • 9Rostamizadeh A. Theoretical foundations and algorithms for learning with multiple kernels[D]. New York: New York University, 2010.
  • 10Kloft M, Brefeld U, Sonnenburg S, et al. Non-sparse regularization for multiple kernel learning[R]. USA: Cornell University, 2010.

引证文献1

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部