本文選題：極化SAR　切入點(diǎn)：特征提取　出處：《電子科技大學(xué)》2016年碩士論文　論文類型：學(xué)位論文

【摘要】：極化SAR憑借其全天時(shí)、全天候的工作特性,已走在了遙感信息獲取技術(shù)的前列。隨著獲取的信息越來越多,如何快速而準(zhǔn)確的解譯這些信息,已成為目前研究的熱點(diǎn)問題。而極化SAR圖像分類作為圖像解譯的重要步驟,引起了學(xué)者越來越多的重視。此外,極化SAR圖像分類在軍事情報(bào)、土地利用、森林監(jiān)測(cè)等多個(gè)領(lǐng)域的作用也不可小覷。因此開展極化SAR圖像分類研究,對(duì)拓寬極化SAR系統(tǒng)的應(yīng)用能力具有重大的現(xiàn)實(shí)意義。顯然,分類特征的提取和分類算法的設(shè)計(jì)是實(shí)現(xiàn)分類的重要前提。信息爆炸時(shí)代衍生出了海量的分類特征,如何從這些特征中挑選最有限、最高效、最本質(zhì)的特征組合,是優(yōu)化特征空間、提高分類器性能的關(guān)鍵。此外,為了將極化SAR更好的運(yùn)用到實(shí)際研究中,也為了從更全面的角度分析問題,文中對(duì)比分析了單、雙、全極化SAR在分類性能上的差異及原因。本文以Radarsat-2和ALOS-PALSAR全極化數(shù)據(jù)為例,重點(diǎn)研究了極化SAR圖像特征提取技術(shù)、極化SAR圖像分類方法、極化SAR圖像分類特征選擇以及單、雙、全極化SAR分類性能對(duì)比等內(nèi)容。主要工作和成果如下:(1)極化SAR圖像特征提取。基于極化SAR的特性,提取了極化比、雷達(dá)植被指數(shù)等極化SAR特有的特征參數(shù);構(gòu)建協(xié)方差矩陣和相干矩陣,提取其元素;依托Cloude分解和Freeman分解,提取目標(biāo)分解參數(shù);基于灰度共生矩陣,提取紋理參數(shù)。至此,共提取了33維分類特征,并重點(diǎn)分析了不同類型的特征對(duì)分類結(jié)果的貢獻(xiàn)度,結(jié)果表明紋理參數(shù)貢獻(xiàn)度最高,極化參數(shù)最低。(2)極化SAR圖像分類算法實(shí)現(xiàn)。本文分別采用支持向量機(jī)和隨機(jī)森林算法,對(duì)實(shí)驗(yàn)區(qū)做監(jiān)督分類,驗(yàn)證了算法在實(shí)驗(yàn)區(qū)內(nèi)的有效性,并對(duì)比分析了二者的分類效果。另外,采用網(wǎng)格搜索法尋得了支持向量機(jī)的最優(yōu)參數(shù)。(3)極化SAR圖像特征選擇。采用遺傳算法,定義適合的適應(yīng)度函數(shù),經(jīng)過多次尋優(yōu)迭代,最終將原始33維特征空間簡(jiǎn)化為10維。采用支持向量機(jī)和隨機(jī)森林算法對(duì)特征選擇前后的分類效果進(jìn)行評(píng)價(jià),結(jié)果顯示二者的整體精度和Kappa系數(shù)均稍有提高。體現(xiàn)了特征選擇的必要性和優(yōu)越性。(4)單、雙、全極化SAR分類性能對(duì)比。從定量和定性角度評(píng)價(jià)分類效果,可得:在分類性能方面,全極化SAR最優(yōu),雙極化次之,單極化最差;分析不同雙極化組合的分類差異,結(jié)果表明HH-VV極化組合可作為全極化SAR的一種合理替代,并從H/α空間相似性的角度給出原因;同樣,對(duì)不同單極化通道的分類效果進(jìn)行評(píng)價(jià),并闡述原因。
[Abstract]:Polarimetric SAR has been in the forefront of remote sensing information acquisition technology with its all-day, all-weather working characteristics. As more and more information is obtained, how to interpret this information quickly and accurately, Polarimetric SAR image classification, as an important step in image interpretation, has attracted more and more attention of scholars. In addition, polarimetric SAR image classification in military information, land use, The role of forest monitoring and other fields can not be underestimated. Therefore, it is of great practical significance to develop the classification of polarized SAR images to broaden the application capability of polarimetric SAR system. The extraction of classification features and the design of classification algorithms are the important prerequisites for classification. In the age of information explosion, there are a lot of classification features derived from them, how to select the most limited, efficient and essential feature combinations from these features. It is the key to optimize the feature space and improve the performance of classifier. In addition, in order to better apply polarized SAR to practical research, and to analyze the problem from a more comprehensive perspective, this paper compares and analyzes single and double, In this paper, we take Radarsat-2 and ALOS-PALSAR full polarization data as examples, we focus on the study of polarimetric SAR image feature extraction technology, polarimetric SAR image classification method, polarization SAR image classification feature selection and single, double, single, double, single, double, single, double, single, double, and single, double, and single, double, and single, double, and single, double, The main work and results are as follows: 1) feature extraction of polarimetric SAR images. Based on the characteristics of polarimetric SAR, the characteristic parameters of polarimetric SAR, such as polarimetric ratio and radar vegetation index, are extracted. The covariance matrix and coherent matrix are constructed to extract the elements; the target decomposition parameters are extracted by Cloude decomposition and Freeman decomposition; the texture parameters are extracted based on gray level co-occurrence matrix. So far, 33 dimensional classification features are extracted. The contribution of different types of features to the classification results is analyzed. The results show that the texture parameters are the highest, and the polarization parameters are the lowest. The polarimetric SAR image classification algorithm is implemented. Support vector machine and stochastic forest algorithm are used in this paper, respectively. The effectiveness of the algorithm in the experimental area is verified by the supervised classification of the experimental area, and the classification effect of the two methods is compared and analyzed. The optimal parameter of support vector machine (SVM) is found by grid search method. The feature selection of polarimetric SAR image is obtained. The fitness function is defined by genetic algorithm, and after several optimization iterations, Finally, the original 33 dimensional feature space is simplified to 10 dimension. Support vector machine and stochastic forest algorithm are used to evaluate the classification effect before and after feature selection. The results show that the overall accuracy and Kappa coefficient of both are improved slightly, which reflects the necessity and superiority of feature selection. The classification performance of single, double and fully polarized SAR is compared. The classification effect is evaluated from quantitative and qualitative aspects. In terms of classification performance, the fully polarized SAR is the best, the double polarization is the second, and the single polarization is the worst. The results show that the HH-VV polarization combination can be used as a reasonable substitute for the fully polarized SAR. The reasons are given from the angle of spatial similarity of H / 偽, and the classification effect of different single-polarization channels is evaluated, and the reasons are explained.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TN957.52

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 ZHANG Kui;DONG Yu;BALL Andrew;;Feature Selection by Merging Sequential Bidirectional Search into Relevance Vector Machine in Condition Monitoring[J];Chinese Journal of Mechanical Engineering;2015年06期

2 郭海京;吳磊;;基于模糊算法的極化SAR影像分類[J];測(cè)繪地理信息;2014年05期

3 劉軒;王衛(wèi)紅;唐曉斌;李鵬;;遺傳算法在SAR圖像目標(biāo)鑒別特征選擇上的應(yīng)用[J];電子科技;2014年05期

4 付姣;張永紅;劉曉龍;孫廣通;;利用Yamaguchi分解保持地物散射特性的極化SAR分類[J];測(cè)繪科學(xué);2014年03期

5 巫兆聰;歐陽群東;李芳芳;;顧及特征優(yōu)化的全極化SAR圖像SVM分類[J];測(cè)繪科學(xué);2013年03期

6 姚旭;王曉丹;張玉璽;權(quán)文;;基于粒子群優(yōu)化算法的最大相關(guān)最小冗余混合式特征選擇方法[J];控制與決策;2013年03期

7 張祥;鄧喀中;范洪冬;趙慧;;基于目標(biāo)分解的極化SAR圖像SVM監(jiān)督分類[J];計(jì)算機(jī)應(yīng)用研究;2013年01期

8 吳克壽;陳玉明;謝榮生;王曉棟;;基于粗糙集與蟻群優(yōu)化算法的特征選擇方法研究[J];計(jì)算機(jī)應(yīng)用研究;2011年07期

9 張中山;燕琴;余潔;李巖;;基于粒子群算法的全極化SAR圖像非監(jiān)督分類算法研究[J];武漢大學(xué)學(xué)報(bào)(信息科學(xué)版);2010年08期

10 朱顥東;鐘勇;;使用優(yōu)化模擬退火算法的文本特征選擇[J];計(jì)算機(jī)工程與應(yīng)用;2010年04期

相關(guān)博士學(xué)位論文 前2條

1 劉華文;基于信息熵的特征選擇算法研究[D];吉林大學(xué);2010年

2 周曉光;極化SAR圖像分類方法研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2008年

相關(guān)碩士學(xué)位論文 前3條

1 喬鑫;極化SAR圖像分類與分類器的回歸實(shí)現(xiàn)[D];西安電子科技大學(xué);2012年

2 丘昌鎮(zhèn);高分辨率SAR圖像目標(biāo)分類特征提取與分析[D];國(guó)防科學(xué)技術(shù)大學(xué);2009年

3 楊智勇;復(fù)雜背景下的文本提取技術(shù)[D];江西師范大學(xué);2004年

，

本文編號(hào)：1602903