本文關(guān)鍵詞： 合成孔徑雷達(dá) 自動(dòng)目標(biāo)識(shí)別 特征提取 稀疏表示 稀疏保持投影　出處：《中國(guó)民航大學(xué)》2014年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：合成孔徑雷達(dá)(Synthetic Aperture Radar,SAR)是一種主動(dòng)的、全天候的遠(yuǎn)程傳感器,可以在白天或者夜晚運(yùn)行,能夠穿透云層,從空中或者空間傳播的平臺(tái)構(gòu)造地面高分辨率圖像,在現(xiàn)代戰(zhàn)場(chǎng)中有很重要的作用�；赟AR的自動(dòng)目標(biāo)識(shí)別(Automatic Target Recognition,ATR)技術(shù)在軍事方面有很重要的應(yīng)用,一直是國(guó)內(nèi)外學(xué)者研究的熱門(mén)課題。近幾年壓縮感知的提出為稀疏表示的發(fā)展提供了工程應(yīng)用的土壤,得到很多學(xué)者的廣泛關(guān)注,并被應(yīng)用到多個(gè)領(lǐng)域,如圖像壓縮、去噪等。之后有學(xué)者將稀疏表示應(yīng)用于圖像識(shí)別中,并在人臉數(shù)據(jù)庫(kù)上進(jìn)行實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果證明該方法能夠取得比傳統(tǒng)方法更好的效果,基于此本文將稀疏表示方法應(yīng)用于SAR圖像目標(biāo)識(shí)別中。首先介紹了稀疏表示的基本理論,包括稀疏字典的構(gòu)造以及稀疏求解算法,在此基礎(chǔ)上研究了稀疏理論在識(shí)別中的應(yīng)用,給出了結(jié)合KPCA(Kernel Principal Component Analysis)和稀疏表示的SAR目標(biāo)識(shí)別方法。該方法首先利用KPCA方法提取樣本特征,然后在特征空間內(nèi)構(gòu)造稀疏表示模型,通過(guò)梯度投影法(Gradient Projection for Sparse Reconstruction,GPSR)求得測(cè)試樣本的稀疏系數(shù),最后根據(jù)稀疏系數(shù)的能量特征進(jìn)行分類(lèi)識(shí)別。利用美國(guó)運(yùn)動(dòng)與靜止目標(biāo)獲取與識(shí)別(Moving and Stationary Target Acquisition and Recognition,MSTAR)實(shí)測(cè)SAR數(shù)據(jù)進(jìn)行實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果表明該方法在方位角未知的情況下能夠明顯提高目標(biāo)的識(shí)別結(jié)果,是一種有效的SAR目標(biāo)識(shí)別方法。另外本文還研究了一種新的特征提取方法即稀疏保持投影(Sparsity Preserving Projections,SPP),該方法將由稀疏表示得到的稀疏系數(shù)引入到特征提取中,通過(guò)數(shù)據(jù)的稀疏重建關(guān)系構(gòu)造目標(biāo)函數(shù)得到特征向量。在該方法的基礎(chǔ)上,本文給出了基于改進(jìn)的稀疏保持投影特征提取方法,該方法在SPP特征提取的基礎(chǔ)上保持樣本之間的稀疏重構(gòu)關(guān)系,同時(shí)借鑒了局部保持投影(Locality preserving Projection,LPP)特征提取方法的思想,使得提取的特征不僅能保持稀疏重構(gòu)特性,還能使同類(lèi)樣本間的距離變小。將改進(jìn)的特征提取方法應(yīng)用到SAR目標(biāo)識(shí)別中,利用MSTAR數(shù)據(jù)進(jìn)行實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果證明了該方法的有效性。
[Abstract]:Synthetic Aperture radar (SAR) is an active, all-weather remote sensor that can operate during the day or at night, can penetrate clouds and construct high-resolution ground images from a platform in the air or in space. The automatic Target recognition (ATR) technology based on SAR has a very important application in the military field. In recent years, compression perception has provided the soil of engineering application for the development of sparse representation, which has been widely concerned by many scholars, and has been applied to many fields, such as image compression. After that, some scholars applied sparse representation to image recognition, and carried out experiments on face database. The experimental results show that this method can achieve better results than traditional methods. In this paper, sparse representation method is applied to SAR image target recognition. Firstly, the basic theory of sparse representation is introduced, including the construction of sparse dictionary and sparse solution algorithm. Based on this, the application of sparse theory in recognition is studied. In this paper, a method of SAR target recognition based on KPCA(Kernel Principal Component Analysis and sparse representation is presented. Firstly, the KPCA method is used to extract the sample features, and then a sparse representation model is constructed in the feature space. The sparse coefficients of test samples are obtained by gradient Projection for Sparse Reconfiguration (GPSRs). Finally, the sparse coefficients are classified and identified according to the energy characteristics of the sparse coefficients. The SAR data of moving and Stationary Target Acquisition and recognition are obtained and recognized by moving and still targets in the United States. The experimental results show that the method can improve the target recognition results obviously when the azimuth is unknown. This paper also studies a new feature extraction method, namely sparse preserving projection Preserving projects, which introduces sparse coefficients obtained from sparse representation into feature extraction. The feature vector is obtained by constructing the objective function through sparse reconstruction of data. Based on this method, an improved sparse preserving projection feature extraction method is presented in this paper. Based on SPP feature extraction, the sparse reconstruction relationship between samples is maintained, and the idea of local preserving projection preserving projection LPP feature extraction is used for reference, so that the extracted features can not only maintain sparse reconstruction characteristics. The improved feature extraction method is applied to SAR target recognition and the experimental results of MSTAR data show that the method is effective.
【學(xué)位授予單位】：中國(guó)民航大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：TN958

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 劉中杰;莊麗葵;曹云峰;丁萌;;基于主元分析和稀疏表示的SAR圖像目標(biāo)識(shí)別[J];系統(tǒng)工程與電子技術(shù);2013年02期

2 方慶;張順生;段昶;;基于壓縮感知的SAR圖像目標(biāo)識(shí)別[J];火控雷達(dá)技術(shù);2012年04期

3 蔡紅;;基于稀疏表示的SAR圖像壓縮方法研究[J];計(jì)算機(jī)工程與應(yīng)用;2012年24期

4 李鄴;陳北京;張旭;舒華忠;;一種結(jié)合稀疏表示和切比雪夫矩的人臉識(shí)別算法[J];東南大學(xué)學(xué)報(bào)(自然科學(xué)版);2012年02期

5 宋相法;焦李成;;基于稀疏表示及光譜信息的高光譜遙感圖像分類(lèi)[J];電子與信息學(xué)報(bào);2012年02期

6 楊旗;薛定宇;崔建江;;基于稀疏表示的步態(tài)識(shí)別[J];東北大學(xué)學(xué)報(bào)(自然科學(xué)版);2012年01期

7 張靜;王國(guó)宏;楊智勇;劉福太;;基于二維子分類(lèi)鑒別分析的SAR圖像識(shí)別方法研究[J];電子學(xué)報(bào);2010年04期

8 賀志國(guó);陸軍;匡綱要;;SAR圖像特征提取與選擇研究[J];信號(hào)處理;2008年05期

9 胡利平;劉宏偉;吳順君;;基于多分類(lèi)器融合的SAR圖像自動(dòng)目標(biāo)識(shí)別方法[J];系統(tǒng)工程與電子技術(shù);2008年05期

10 韓萍,吳仁彪,王兆華;基于KFD準(zhǔn)則的SAR目標(biāo)特征提取與識(shí)別[J];現(xiàn)代雷達(dá);2004年07期

相關(guān)碩士學(xué)位論文 前2條

1 高敏;基于CS的SAR目標(biāo)識(shí)別[D];西安電子科技大學(xué);2010年

2 韓征;基于投影特征的SAR自動(dòng)目標(biāo)識(shí)別技術(shù)研究[D];中國(guó)民航大學(xué);2009年

，

本文編號(hào)：1540369