基于深度學(xué)習的SAR目標識別方法研究
發(fā)布時間：2019-04-19 22:01
【摘要】：合成孔徑雷達(Synthetic Aperture Radar,SAR)由于其獨特的優(yōu)勢已經(jīng)成為當今社會的一種重要的信息獲取手段,無論在軍用領(lǐng)域還是民用領(lǐng)域都發(fā)揮著至關(guān)重要的作用。作為獲取SAR信息的方式,SAR圖像的識別一直是研究熱點之一。近年來深度學(xué)習的提出引起了又一股人工智能的研究熱,深度學(xué)習由于將非監(jiān)督學(xué)習和監(jiān)督學(xué)習結(jié)合,使得大量的無標簽的數(shù)據(jù)都有了學(xué)習的價值,因而在目標識別方面取得了前所未有的成功,但仍面臨著許多問題。本文首先總結(jié)了基于機器學(xué)習的SAR圖像目標識別的技術(shù),給出了監(jiān)督學(xué)習中的神經(jīng)網(wǎng)絡(luò)和非監(jiān)督學(xué)習中的主成分分析兩種方法在MSTAR數(shù)據(jù)集上的識別效果;其次本文指出了機器學(xué)習方法在目標識別方面的局限,即:在應(yīng)用到SAR圖像目標識別時需要大量的專業(yè)知識,不能自動的提取能夠表征SAR目標的特征,基于此,本文提出了深度學(xué)習的模型可以解決該問題,分別將深度置信網(wǎng)絡(luò)和卷積神經(jīng)網(wǎng)絡(luò)兩種深度學(xué)習模型用于SAR圖像目標識別,并分析了兩種模型的各個參數(shù)對模型的性能的影響,給出了在用于識別SAR目標時的這些參數(shù)的典型值;最后,由于SAR圖像中包含大量的相干斑噪聲,這是影響模型識別性能的關(guān)鍵因素之一,本文在對比了Lee濾波和小波變換兩種相干斑噪聲抑制方法的識別效果的基礎(chǔ)上,得出結(jié)論:Lee濾波和二層小波變換兩種方法的結(jié)合可以獲得在識別性能方面的提升。
[Abstract]:Because of its unique advantages, synthetic aperture radar (Synthetic Aperture Radar,SAR) has become an important means of information acquisition in today's society. It plays an important role in both military and civilian fields. As a way to obtain SAR information, SAR image recognition has always been one of the research hotspots. In recent years, the proposal of in-depth learning has caused another hot research in artificial intelligence. Because of the combination of unsupervised learning and supervised learning, a large number of unlabeled data have the value of learning. As a result, it has achieved unprecedented success in target recognition, but it still faces many problems. In this paper, the technology of SAR image target recognition based on machine learning is summarized, and the recognition effects of neural network in supervised learning and principal component analysis in unsupervised learning on MSTAR data sets are given. Secondly, this paper points out the limitation of machine learning method in target recognition, that is, when it is applied to SAR image target recognition, it needs a lot of professional knowledge, and can not automatically extract the features of SAR target, which is based on this. In this paper, a depth learning model is proposed to solve this problem. Two depth learning models, depth confidence network and convolution neural network, are applied to target recognition of SAR images, and the influence of each parameter of the two models on the performance of the model is analyzed. The typical values of these parameters used to identify SAR targets are given. Finally, because there is a lot of speckle noise in the SAR image, which is one of the key factors affecting the performance of model recognition, this paper compares the recognition effects of two coherent speckle suppression methods, Lee filter and wavelet transform, based on the comparison of the recognition results of the two coherent speckle suppression methods, Lee filtering and wavelet transform. It is concluded that the combination of Lee filtering and bilevel wavelet transform can improve the recognition performance.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：TN957.52
本文編號：2461327
[Abstract]:Because of its unique advantages, synthetic aperture radar (Synthetic Aperture Radar,SAR) has become an important means of information acquisition in today's society. It plays an important role in both military and civilian fields. As a way to obtain SAR information, SAR image recognition has always been one of the research hotspots. In recent years, the proposal of in-depth learning has caused another hot research in artificial intelligence. Because of the combination of unsupervised learning and supervised learning, a large number of unlabeled data have the value of learning. As a result, it has achieved unprecedented success in target recognition, but it still faces many problems. In this paper, the technology of SAR image target recognition based on machine learning is summarized, and the recognition effects of neural network in supervised learning and principal component analysis in unsupervised learning on MSTAR data sets are given. Secondly, this paper points out the limitation of machine learning method in target recognition, that is, when it is applied to SAR image target recognition, it needs a lot of professional knowledge, and can not automatically extract the features of SAR target, which is based on this. In this paper, a depth learning model is proposed to solve this problem. Two depth learning models, depth confidence network and convolution neural network, are applied to target recognition of SAR images, and the influence of each parameter of the two models on the performance of the model is analyzed. The typical values of these parameters used to identify SAR targets are given. Finally, because there is a lot of speckle noise in the SAR image, which is one of the key factors affecting the performance of model recognition, this paper compares the recognition effects of two coherent speckle suppression methods, Lee filter and wavelet transform, based on the comparison of the recognition results of the two coherent speckle suppression methods, Lee filtering and wavelet transform. It is concluded that the combination of Lee filtering and bilevel wavelet transform can improve the recognition performance.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：TN957.52
【參考文獻】
相關(guān)期刊論文 前4條
1 王雅思;姚鴻勛;孫曉帥;許鵬飛;趙思成;;深度學(xué)習中的自編碼器的表達能力研究[J];計算機科學(xué);2015年09期
2 劉建偉;劉媛;羅雄麟;;深度學(xué)習研究進展[J];計算機應(yīng)用研究;2014年07期
3 賈承麗;趙凌君;吳其昌;匡綱要;;基于遺傳算法的SAR圖像道路網(wǎng)檢測方法[J];計算機學(xué)報;2007年07期
4 程輝;于秋則;田金文;柳健;;基于小波支持向量機分割的SAR圖像橋梁目標檢測[J];華中科技大學(xué)學(xué)報(自然科學(xué)版);2006年04期
，本文編號：2461327
本文鏈接：http://www.sikaile.net/kejilunwen/xinxigongchenglunwen/2461327.html
最近更新
教材專著
