寬帶雷達(dá)光學(xué)區(qū)頻域識(shí)別法
FREQUENCY-DOMAIN RECOGNITION METHOD FOR WIDEBAND RADAR OPTICAL REGION TARGET
-
摘要: 該文以寬帶雷達(dá)光學(xué)區(qū)目標(biāo)識(shí)別為背景,由頻域測(cè)量數(shù)據(jù)構(gòu)造了不隨目標(biāo)距離像沿徑向平移而改變的頻域波形回波幅值波形和相位特征波形;基于此波形,提取了兩種對(duì)目標(biāo)方位角不敏感的識(shí)別特征廣義頻數(shù)和波形長(zhǎng)度;并借助于時(shí)頻分析中尺度變換的概念,把特征集進(jìn)一步完備化。針對(duì)頻域直接識(shí)別法易受測(cè)量噪聲影響的缺點(diǎn),設(shè)計(jì)了相應(yīng)的預(yù)處理算法。選用FMM神經(jīng)網(wǎng)絡(luò)作為分類(lèi)器,并修改了它傳統(tǒng)的學(xué)習(xí)算法。對(duì)5種噴氣飛機(jī)模型的識(shí)別結(jié)果表明,該算法具有較高的正確識(shí)別率。Abstract: Meeting the application requirements of wideband radar optical region target recognition, this paper presents a simple and effective frequency-domain recognition method. First, two kinds of waves called backscattering amplitude wave and phase feature wave are constructed directly from frequency measured data sets, which keep invariant on the shift of target in the radial direction. Based on these waves, generalized frequency and length of wave are extracted as recognition features insensitive to target azimuth. With the aid of the idea of ruler transform in time-frequency analysis, the feature sets are further completed. Aiming at lessening the effect of measuring noise, the paper then designs a specific preprocessing method. FMM neural network is chosen as the classifier with modified training algorithm. The recog- nition results show that this target recognition algorithm can obtain high correct classification rate.
-
W.M. Steedly, R. L. Moses, High resolution exponential modeling of fully polarized radar returns,IEEE Trans. on AES, 1991, 27(3), 459-468.[2]王雪松,莊釗文,肖順平等,光學(xué)區(qū)雷達(dá)目標(biāo)空間極化結(jié)構(gòu)特性描述及識(shí)別研究,電子學(xué)報(bào),1998,26(6),36-41.[3]肖順平,郭桂蓉,莊釗文等,基于含最小二乘估計(jì)曲線擬合的極化雷達(dá)目標(biāo)識(shí)別方法,電子學(xué)報(bào),1997,25(3),32-36.[4]王雪松,肖順平,莊釗文,基于改進(jìn)退火法擬合參數(shù)估計(jì)的極化雷達(dá)目標(biāo)識(shí)別,現(xiàn)代雷達(dá),1997,19(2),6-11.[5]肖順平,莊釗文,王雪松等,目標(biāo)動(dòng)態(tài)極化結(jié)構(gòu)特征提取與識(shí)別,電子學(xué)報(bào),1998,26(3),48-52.[6]肖順平,王雪松,莊釗文,基于極化不變量的飛機(jī)目標(biāo)識(shí)別,紅外與毫米波學(xué)報(bào),1996,15(6),439-444[7]肖順平,王雪松,郭桂蓉等,基于極化域能量譜的飛機(jī)目標(biāo)識(shí)別,宇航學(xué)報(bào),1998,19(3),23-28.[8]肖懷鐵,莊釗文,郭桂蓉,基于遞歸神經(jīng)網(wǎng)絡(luò)的飛機(jī)目標(biāo)識(shí)別方法,國(guó)防科技大學(xué)學(xué)報(bào),1997,19(4),48 53.[9]A. Zyweck, R. E. Bogner, Radar target classification of commercial aircraft, IEEE Trans. on AES, 1996, 32(2), 598-660.[10]R. Bhatnagar, R. Horvitz, R. Williams, A hybrid system for target classification, Patt. Recog.Lett., 1997, 18, 1399-1403.[11]J. S. Chen, E. K. Walton, Comparison of two target classification techniques, IEEE Trans. on AES, 1986, 22(1), 15-21.[12]P. K. Simpson, Fuzzy min-max neural network-Part 1: classification, IEEE Trans. on Neural Networks, 1992, 3(5), 776-786. -
計(jì)量
- 文章訪問(wèn)數(shù): 2544
- HTML全文瀏覽量: 109
- PDF下載量: 811
- 被引次數(shù): 0
下載:
