發(fā)布時間：2018-04-30 05:42

  本文選題：極化SAR + 支持向量積��； 參考：《西安電子科技大學(xué)》2014年碩士論文

【摘要】：極化合成孔徑雷達(dá)(Pol-SAR)是一個全天候,多通道,多參數(shù)的雷達(dá)成像系統(tǒng),它可以獲得一定波長和視角下目標(biāo)的極化散射信息。和合成孔徑雷達(dá)(SAR)比較,極化SAR擁有更豐富的極化內(nèi)容,再加上極化SAR數(shù)據(jù)具有高維性,并且數(shù)據(jù)相對較復(fù)雜,如何結(jié)合現(xiàn)有的技術(shù)對極化SAR數(shù)據(jù)進(jìn)行高效、準(zhǔn)確的分類已成為極化SAR領(lǐng)域的研究熱點。為了克服傳統(tǒng)的分類方法時間復(fù)雜度過高的問題,本文提出了基于支持向量的聚類方法。由于極化SAR存在著較大的相干斑噪聲,對后續(xù)的分類產(chǎn)生了極大的影響,所以本文根據(jù)相干斑噪聲模型,提出了利用面向?qū)ο蟮姆椒▽O化SAR進(jìn)行分類,其主要工作如下:(1).本文提出了基于面向?qū)ο蠛蚐VM的極化SAR分類方法。傳統(tǒng)的SVM分類精度高,速度快,但是其分類極化SAR時易受相干斑噪聲影響、分類雜點較多,本文將基于像素的極化SAR分類和基于區(qū)域的極化SAR分類方法進(jìn)行了有效的結(jié)合,首先將極化SAR數(shù)據(jù)的相干矩陣T利用SVM進(jìn)行分類得到初始分類,然后將極化SAR數(shù)據(jù)的Pauli特征利用面向?qū)ο蟮姆椒ㄟM(jìn)行過分割,最后在過分割的圖像上對SVM的初始分類結(jié)果利用投票的方式進(jìn)行二次分類,從而得到最終結(jié)果。由于該方法有效的利用了極化SAR數(shù)據(jù)的散射以及空間信息,所以具有不受相干斑噪聲影響,邊緣保持好,準(zhǔn)確率高等優(yōu)點。(2).本文提出了基于面向?qū)ο蠛妥V聚類的極化SAR分類方法。傳統(tǒng)的面向?qū)ο蟮姆椒ǹ梢詫D像進(jìn)行過分割,但是過分割后如何高效的融合是一個問題。譜聚類可以對極化數(shù)據(jù)進(jìn)行很好的分類,但是當(dāng)數(shù)據(jù)量大時,時間復(fù)雜度高,容易造成內(nèi)存溢出。本文提出的方法首先利用面向?qū)ο蟮姆椒▽O化SAR數(shù)據(jù)進(jìn)行過分割,從而起到降維的目的,然后將過分割后的圖像的每一個單元塊當(dāng)做一個對象,然后對這些對象進(jìn)行譜聚類,最后將圖像以對象為基本單元進(jìn)行分類。由于該方法利用面向?qū)ο蟮姆椒▽O化SAR進(jìn)行了降維,所以時間復(fù)雜度大大降低,又因為是以對象為單元進(jìn)行聚類,所以很好的克服了噪聲的影響。(3).本文提出了基于支持向量積和譜聚類的極化SAR分類方法。譜聚類是以譜圖理論為基礎(chǔ)的,和傳統(tǒng)的聚類方法比,它有著很多優(yōu)點,比如在任意的樣本空間都可以聚類并且能收斂于全局最優(yōu)解、對不規(guī)則數(shù)據(jù)不敏感、準(zhǔn)確率高等。但極化SAR數(shù)據(jù)量通常很大,直接求解其相似度矩陣不可行。所以本文提出了先降維后聚類的方法。首先選擇少量樣本,對其利用快速SVM進(jìn)行訓(xùn)練,從而得到其支持向量,然后利用譜聚類對支持向量進(jìn)行聚類,并計算出相應(yīng)的類心,最后計算剩余樣本到各個類心的距離并進(jìn)行分類。和SVM類比,該方法可以有效的提高分類準(zhǔn)確率,并解決了譜聚類中數(shù)據(jù)量過大,內(nèi)存容易溢出和計算復(fù)雜度過高的問題。
[Abstract]:Polarimetric synthetic Aperture Radar (Pol-SAR) is an all-weather, multi-channel, multi-parameter radar imaging system, which can obtain polarimetric scattering information of targets at a certain wavelength and angle of view. Compared with synthetic Aperture Radar (SAR), polarimetric SAR has much richer polarization content, and polarization SAR data have high dimension and relatively complex data. Accurate classification has become a research hotspot in polarized SAR field. In order to overcome the problem of high time complexity of traditional classification methods, a support vector based clustering method is proposed in this paper. Due to the existence of large speckle noise in polarized SAR, it has a great influence on the subsequent classification. In this paper, based on the speckle noise model, an Object-Oriented method is proposed to classify polarized SAR. The main work is as follows: 1. In this paper, a polarimetric SAR classification method based on object oriented and SVM is proposed. The traditional SVM classification method has high accuracy and high speed, but it is easy to be affected by speckle noise when it is classified by polarized SAR, and there are many clutter. In this paper, the polarimetric SAR classification based on pixel and the polarimetric SAR classification method based on region are effectively combined. First, the coherent matrix T of polarized SAR data is classified by SVM to get the initial classification, then the Pauli feature of polarized SAR data is over-partitioned by object-oriented method. Finally, the initial classification results of SVM are classified by voting method on the over-segmented image, and the final results are obtained. Due to the effective use of scattering and spatial information from polarized SAR data, this method has the advantages of not affected by speckle noise, good edge maintenance and high accuracy. In this paper, a polarimetric SAR classification method based on object-oriented and spectral clustering is proposed. The traditional object-oriented method can over-segment the image, but how to fuse efficiently after over-segmentation is a problem. Spectral clustering can classify polarimetric data well, but when the data is large, the time complexity is high, which can easily cause memory overflow. The method proposed in this paper firstly uses the object-oriented method to over-partition the polarimetric SAR data so as to reduce the dimension. Then, each unit block of the over-segmented image is treated as an object, and then these objects are clustered by spectrum. Finally, the image is classified with object as the basic unit. Because the method reduces the dimension of polarized SAR by using object-oriented method, the time complexity is greatly reduced, and because the object is taken as the unit to cluster, it can overcome the influence of noise. In this paper, a polarimetric SAR classification method based on support vector product and spectral clustering is proposed. Spectral clustering is based on spectral graph theory. Compared with traditional clustering method, it has many advantages, such as clustering in arbitrary sample space, convergence to global optimal solution, insensitivity to irregular data, high accuracy and so on. However, the amount of polarimetric SAR data is usually very large, so it is not feasible to solve the similarity matrix directly. So this paper puts forward the method of reducing dimension first and then clustering. Firstly, a small number of samples are selected, and the support vectors are obtained by using fast SVM, then the support vectors are clustered by spectral clustering, and the corresponding cluster centers are calculated. Finally, the distance between the remaining samples and each class center is calculated and classified. Compared with SVM, this method can effectively improve the classification accuracy, and solve the problems of too large amount of data in spectral clustering, easy memory overflow and high computational complexity.
【學(xué)位授予單位】：西安電子科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TN957.52

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王娜;杜海峰;莊健;余進(jìn)濤;王孫安;;三種典型的基于圖分割的譜聚類方法比較[J];系統(tǒng)仿真學(xué)報;2009年11期

2 王會青;陳俊杰;;基于圖劃分的譜聚類方法的研究[J];計算機(jī)工程與設(shè)計;2011年01期

3 王春騰;符傳誼;邢潔清;;基于非負(fù)約束的譜聚類方法[J];電腦知識與技術(shù);2011年17期

4 何飛;王曉晨;馬粹;梁治國;;生產(chǎn)狀態(tài)的測地距離譜聚類分析[J];計算機(jī)工程與應(yīng)用;2012年24期

5 薛寧靜;;生產(chǎn)狀態(tài)的熵值評估譜聚類分析[J];計算機(jī)工程與應(yīng)用;2012年19期

6 管濤;王杰;;譜聚類的算子理論研究進(jìn)展[J];計算機(jī)科學(xué);2013年S1期

7 周文剛;陳雷霆;董仕;;基于譜聚類的網(wǎng)絡(luò)流量分類識別算法[J];電子測量與儀器學(xué)報;2013年12期

8 王玲;薄列峰;焦李成;;密度敏感的半監(jiān)督譜聚類[J];軟件學(xué)報;2007年10期

9 林立;胡俠;朱俊彥;;基于譜聚類的多文檔摘要新方法[J];計算機(jī)工程;2010年22期

10 劉馨月;李靜偉;于紅;尤全增;林鴻飛;;基于共享近鄰的自適應(yīng)譜聚類[J];小型微型計算機(jī)系統(tǒng);2011年09期

相關(guān)博士學(xué)位論文 前1條

1 孔敏;關(guān)聯(lián)圖的譜分析及譜聚類方法研究[D];安徽大學(xué);2006年

相關(guān)碩士學(xué)位論文 前10條

1 陳昭彤;基于拓?fù)鋭莺妥V聚類的社區(qū)發(fā)現(xiàn)研究[D];中國礦業(yè)大學(xué);2015年

2 何心琪;基于譜聚類的水聲圖像分割技術(shù)研究[D];哈爾濱工程大學(xué);2013年

3 趙冬琴;基于譜聚類的MCI影像學(xué)分類特征研究與應(yīng)用[D];太原理工大學(xué);2014年

4 張俊英;基于譜聚類的圖書目錄重構(gòu)[D];浙江大學(xué);2010年

5 張?zhí)鞆?qiáng);基于譜聚類的親友通話圈挖掘[D];華南理工大學(xué);2013年

6 鄭偉;基于核與特征選擇的譜聚類社區(qū)檢測算法[D];西安電子科技大學(xué);2013年

7 朱正偉;譜聚類研究及其在入侵檢測中的應(yīng)用[D];重慶大學(xué);2010年

8 由里;基于譜聚類的圖像分割方法研究[D];國防科學(xué)技術(shù)大學(xué);2011年

9 張洪;結(jié)合概率潛在語義分析的文本譜聚類研究[D];重慶大學(xué);2012年

10 陳志豪;基于阻尼距離的譜聚類集成算法研究與實現(xiàn)[D];華南理工大學(xué);2013年

，

本文編號：1823348