基于神經(jīng)網(wǎng)絡的雷達目標識別
RADAR TARGET RECOGNITION BASED ON NEURAL NETWORK
-
摘要: 本文討論了基于徑向基函數(shù)網(wǎng)絡(RBFN)的雷達目標識別問題。在分析了一維距離象特點的基礎(chǔ)上,提出了采用非相關(guān)幅度平均一維距離象以獲取穩(wěn)定模式這一有效方法。在指出傳統(tǒng)經(jīng)驗公式局限性后,給出了一種基于訓練樣本空間分布來估計高斯核函數(shù)形狀參數(shù)的方法。用微波暗室試驗數(shù)據(jù)進行轉(zhuǎn)臺成象并對一維距離象三種模式進行識別分類的結(jié)果表明,本文所提出的方法用于研究雷達目標識別是有效的。
-
關(guān)鍵詞:
- 神經(jīng)網(wǎng)絡; 徑向基函數(shù); 距離象; 目標識別
Abstract: The problem of radar target recognition based on a radial basis function network is discussed. On the basis of analyzing the features of one-dimensional range profile, an effective method is proposed, which performs amplitude average of the range profiles to obtain more stable patterns. After pointing out the limitedness of traditional experimental formula, this paper also gives a method of estimating the shape parameter of a Guassian kernel function based on the spacial distribution of training samples.It is shown from theoretical analysis and experimental results of rotating platform imaging based on data acquired in a microwave anechoic chamber that the method proposed in this paper is promissing in the application of radar target recognition. -
Bhanu B. IEEE Trans. on AES, 1986, AES-22(4): 364-379.[2]Roth M W. IEEE Trans. on NN, 1990. NN-1(1): 28-43.[3]Farhat N H. Proc[J].IEEE.1989, 77(5):670-680[4]Beastall W D. Recognition of radar signals by neural network.[5]First IEE ICANN, London: 1989, 139-142.[6]Vrckovnik G, et al. Radial basis function classification of impulsed radar waveforms, Proc, of International Joint Conferencr. on Neural Network, Vol. 1, LS90. 45-50.[7]目標識別課題組.雷達目標特性測試、識別與分類研究報告--目標一維成象及識別技術(shù).西安:西安電子科技大學電子工程研究所研究報告,1992.12.[8]]Renals S, et al. Phoneme classification experiments using radial basis functions, Proc. of International Joint Conference on Neural Network, Vol. I, 1989 461-467.[9]Poggio T, et al. Proc. IEEE, 1990, 78(9).[10]Koontz W L G, Fukunaga K. IEEE Trans, on C, 1972,C-21(9): 976-974.[11]邊肇祺.模式識別.北京:清華大學出版社,第九章.[12]黃德雙. 雷達目標一維象識別技術(shù)研究:[博士論文].西安:西安電子科技大學,1992.[13]保錚,鄧文彪,楊軍.電子學報,1992，20(6): 1-6. -
計量
- 文章訪問數(shù): 2503
- HTML全文瀏覽量: 293
- PDF下載量: 493
- 被引次數(shù): 0
下載:
