基于流形學習的高分辨率SAR影像城市地物特征提取方法研究
發(fā)布時間：2018-08-02 21:14
【摘要】：合成孔徑雷達(SAR)能夠穿云透霧,具有全天時全天候監(jiān)測的獨特優(yōu)勢,能夠彌補光學傳感器在多云雨霧地區(qū)無法獲取有效數(shù)據(jù)的缺陷,已成為遙感信息提取的重要手段。隨著高分SAR衛(wèi)星的陸續(xù)發(fā)射,城市典型地物提取已成為高分SAR的應(yīng)用熱點,可為城市規(guī)劃、土地利用監(jiān)測、人口密度調(diào)查等提供可持續(xù)的科學基礎(chǔ)數(shù)據(jù)。由于高分辨率SAR影像城市地物復(fù)雜的散射特性,目前基于高分辨率SAR數(shù)據(jù)的典型地物提取的精度不高。同時,高分辨率SAR影像的高維非線性特點使城市典型地物自動提取的難度加大。流形學習作為一類機器學習的新方法,能夠發(fā)現(xiàn)高維空間數(shù)據(jù)的內(nèi)在本質(zhì)特征。將善于處理非線性數(shù)據(jù)的流形學習方法應(yīng)用于高分辨率SAR影像的特征提取,有利于提高目標識別精度。因此,為提高城市典型地物識別和提取精度,研究典型地物自動提取技術(shù),論文研究基于流形學習方法的高分辨率SAR影像城市典型地物特征提取與識別方法。主要研究內(nèi)容如下:(1)分析了高分辨率SAR影像的城市典型地物特征并構(gòu)建了高維特征集。首先,從幾何特征、輻射特征及各城市地物的圖像特征對高分辨率SAR影像進行了詳細的分析;其次,利用經(jīng)典的二階概率統(tǒng)計方法灰度共生矩陣(Gray Level Co-occurrence Matrix,GLCM)提取了圖像8種紋理特征,與圖像的灰度特征構(gòu)建SAR影像的高維特征集;最后,通過實驗分析,確定了紋理特征提取的最佳窗口參數(shù)。(2)分別選擇拉普拉斯特征映射(Laplacian Eigenmap,LE)、局部線性嵌入(Locally Linear Embedding,LLE)、Hessian局部線性嵌入算法(Hessian Locally Linear Embedding,HLLE)、局部切空間排列(Local Tangent Space Alignment,LTSA)、局部保持投影(Locality Preserving Projections,LPP)5種典型的流形學習方法對三種城市典型地物類型(建筑區(qū)、水體、體育場)的高維特征集進行降維,最終提取出三種地物類型,并對5種方法提取的結(jié)果進行精度評價,綜合分析了各種方法的優(yōu)缺點。(3)對選擇的局部切空間排列(Local Tangent Space Alignment,LTSA)方法,針對高分SAR數(shù)據(jù)分布不均的情況進行改進。綜合考慮流形形態(tài)結(jié)構(gòu)與樣本鄰域的歐式距離,對原方法的切空間估計進行加權(quán)改進,提出了一種基于距離與結(jié)構(gòu)加權(quán)的局部切空間排列算法(Distance and Structure Weighting Local Tangent Space Alignment,DSWLTSA),并將算法應(yīng)用到高分SAR圖像高維特征集的維數(shù)約簡中。以3種典型的地物為例,通過實驗對DSWLTSA和LTSA算法進行對比分析,驗證了DSWLTSA算法的有效性;通過實驗深入的分析了DSWLTSA算法的適用性和應(yīng)用價值。(4)針對局部線性嵌入算法(Locally Linear Embedding,LLE)對于樣本采樣稀疏效果不好的問題,提出一種基于均勻化樣本距離的LLE算法(Distance Homogenization Locally Linear Embedding,DHLLE),新的方法通過對樣本之間距離的重新計算,使問題得到改善。將算法應(yīng)用到高分SAR圖像高維特征集的維數(shù)約簡中。驗證了LLE算法與DHLLE算法對城市典型地物的識別能力,并對比分析了DHLLE算法與DSWLTSA算法的優(yōu)缺點。
[Abstract]:Synthetic aperture radar (SAR) can wear cloud permeable fog, and has the unique advantage of all-weather all weather monitoring. It can make up for the defect that optical sensor can not obtain effective data in the cloudy and fog area. It has become an important means of remote sensing information extraction. With the launching of high SAR satellite, the city typical ground extraction has become a high grade SAR Hot spots provide sustainable scientific basic data for urban planning, land use monitoring, population density survey and so on. Due to the complex scattering characteristics of high resolution SAR images, the accuracy of typical terrain extraction based on high resolution SAR data is not high. At the same time, high dimensional nonlinear characteristics of high resolution SAR images make cities The difficulty of automatic extraction of typical objects is more difficult. Manifold learning, as a new method of machine learning, can discover the intrinsic characteristics of high dimensional spatial data. The manifold learning method, which is good at dealing with nonlinear data, is applied to the feature extraction of high resolution SAR images, which is helpful to improve the accuracy of target recognition. Therefore, to improve the city code The automatic extraction technology of typical ground objects is studied and the method of extracting and identifying the typical features of the city based on the manifold learning method is studied in this paper. The main research contents are as follows: (1) the characteristics of the city canonical features of high resolution SAR images are analyzed and the high vate collection is constructed. First, the SAR feature collection is constructed. The high resolution SAR images are analyzed in detail. Secondly, 8 texture features are extracted by the classical two order probability statistical method of Gray Level Co-occurrence Matrix (GLCM), and the high Vitter collection of the SAR image is constructed with the gray features of the image. Finally, through the experimental analysis, the optimum window parameters for texture feature extraction are determined. (2) select Laplasse Eigenmap (LE), local linear embedding (Locally Linear Embedding, LLE), Hessian local linear embedding algorithm (Hessian Locally Linear Embedding,), local tangent space arrangement Alignment, LTSA), Locality Preserving Projections (LPP), 5 typical manifold learning methods are used to reduce the dimension of the high Vette collection of three typical types of city objects (construction area, water body, stadium), and finally extract three types of ground objects, and evaluate the accuracy of the results extracted by the 5 methods. The advantages and disadvantages of the method. (3) to improve the Local Tangent Space Alignment (LTSA) method, to improve the uneven distribution of the high grade SAR data. Considering the Euclidean distance between the shape structure of the manifold and the neighborhood of the sample, a weighted improvement is made for the estimation of the tangent space of the original method, and a kind of distance and junction based on the distance and knot is proposed. The weighted local tangent spatial arrangement algorithm (Distance and Structure Weighting Local Tangent Space Alignment, DSWLTSA) is applied to the dimensionality reduction of high grade SAR image high vet collection. The validity of the algorithm is verified by comparison and analysis of DSWLTSA and LTSA calculations with 3 typical terrain objects. The applicability and application value of DSWLTSA algorithm are analyzed through experiments. (4) a LLE algorithm based on homogeneous sample distance (Distance Homogenization Locally Linear Embedding, DHLLE) is proposed for local linear embedding algorithm (Locally Linear Embedding, LLE), which is not good for sample sampling sparse results. The algorithm improves the problem by recalculating the distance between samples. The algorithm is applied to the dimensionality reduction of high SAR image high VAT collection. The recognition ability of LLE and DHLLE algorithm for typical urban terrain is verified, and the advantages and disadvantages of DHLLE algorithm and DSWLTSA algorithm are compared and analyzed.
【學位授予單位】：中國科學院大學(中國科學院遙感與數(shù)字地球研究所)
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：P237
本文編號：2160745
[Abstract]:Synthetic aperture radar (SAR) can wear cloud permeable fog, and has the unique advantage of all-weather all weather monitoring. It can make up for the defect that optical sensor can not obtain effective data in the cloudy and fog area. It has become an important means of remote sensing information extraction. With the launching of high SAR satellite, the city typical ground extraction has become a high grade SAR Hot spots provide sustainable scientific basic data for urban planning, land use monitoring, population density survey and so on. Due to the complex scattering characteristics of high resolution SAR images, the accuracy of typical terrain extraction based on high resolution SAR data is not high. At the same time, high dimensional nonlinear characteristics of high resolution SAR images make cities The difficulty of automatic extraction of typical objects is more difficult. Manifold learning, as a new method of machine learning, can discover the intrinsic characteristics of high dimensional spatial data. The manifold learning method, which is good at dealing with nonlinear data, is applied to the feature extraction of high resolution SAR images, which is helpful to improve the accuracy of target recognition. Therefore, to improve the city code The automatic extraction technology of typical ground objects is studied and the method of extracting and identifying the typical features of the city based on the manifold learning method is studied in this paper. The main research contents are as follows: (1) the characteristics of the city canonical features of high resolution SAR images are analyzed and the high vate collection is constructed. First, the SAR feature collection is constructed. The high resolution SAR images are analyzed in detail. Secondly, 8 texture features are extracted by the classical two order probability statistical method of Gray Level Co-occurrence Matrix (GLCM), and the high Vitter collection of the SAR image is constructed with the gray features of the image. Finally, through the experimental analysis, the optimum window parameters for texture feature extraction are determined. (2) select Laplasse Eigenmap (LE), local linear embedding (Locally Linear Embedding, LLE), Hessian local linear embedding algorithm (Hessian Locally Linear Embedding,), local tangent space arrangement Alignment, LTSA), Locality Preserving Projections (LPP), 5 typical manifold learning methods are used to reduce the dimension of the high Vette collection of three typical types of city objects (construction area, water body, stadium), and finally extract three types of ground objects, and evaluate the accuracy of the results extracted by the 5 methods. The advantages and disadvantages of the method. (3) to improve the Local Tangent Space Alignment (LTSA) method, to improve the uneven distribution of the high grade SAR data. Considering the Euclidean distance between the shape structure of the manifold and the neighborhood of the sample, a weighted improvement is made for the estimation of the tangent space of the original method, and a kind of distance and junction based on the distance and knot is proposed. The weighted local tangent spatial arrangement algorithm (Distance and Structure Weighting Local Tangent Space Alignment, DSWLTSA) is applied to the dimensionality reduction of high grade SAR image high vet collection. The validity of the algorithm is verified by comparison and analysis of DSWLTSA and LTSA calculations with 3 typical terrain objects. The applicability and application value of DSWLTSA algorithm are analyzed through experiments. (4) a LLE algorithm based on homogeneous sample distance (Distance Homogenization Locally Linear Embedding, DHLLE) is proposed for local linear embedding algorithm (Locally Linear Embedding, LLE), which is not good for sample sampling sparse results. The algorithm improves the problem by recalculating the distance between samples. The algorithm is applied to the dimensionality reduction of high SAR image high VAT collection. The recognition ability of LLE and DHLLE algorithm for typical urban terrain is verified, and the advantages and disadvantages of DHLLE algorithm and DSWLTSA algorithm are compared and analyzed.
【學位授予單位】：中國科學院大學(中國科學院遙感與數(shù)字地球研究所)
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：P237
【參考文獻】
相關(guān)期刊論文 前10條
1 劉欣;張繼賢;趙爭;馬安東;王萍;;多特征加權(quán)融合的高分SAR影像建筑區(qū)提取方法[J];測繪科學;2016年04期
2 肖紅光;文俊;陳立福;史長瓊;;一種新的高分辨率SAR圖像道路提取算法[J];計算機工程與應(yīng)用;2016年15期
3 李雪薇;郭藝友;方濤;;基于對象的合成孔徑雷達影像極化分解方法[J];計算機應(yīng)用;2014年05期
4 李世偉;王召巴;楊建生;;基于遙感的城市典型地物信息的快速獲取方法[J];計算機工程與設(shè)計;2014年03期
5 張紅;葉曦;王超;張波;吳樊;湯益先;;面向?qū)ο蟮母叻直媛蔛AR圖像處理及應(yīng)用[J];中國圖象圖形學報;2014年03期
6 趙凌君;譚熙;匡綱要;;基于變差函數(shù)模型擬合的城區(qū)SAR圖像分類新方法[J];現(xiàn)代雷達;2014年02期
7 余潔;劉振宇;燕琴;楊杰;;結(jié)合統(tǒng)計和形狀特征的高分辨率SAR影像道路網(wǎng)提取[J];武漢大學學報(信息科學版);2013年11期
8 徐佳;陳媛媛;黃其歡;何秀鳳;;綜合灰度與紋理特征的高分辨率星載SAR圖像建筑區(qū)提取方法研究[J];遙感技術(shù)與應(yīng)用;2012年05期
9 王壽彪;楊桄;丁文東;張儉峰;;SAR圖像目標識別特征提取與選擇方法研究進展[J];科技情報開發(fā)與經(jīng)濟;2011年26期
10 劉雅軒;張小雷;雷軍;朱磊;;新疆綠洲城市空間擴展特征及其驅(qū)動力分析[J];中國沙漠;2011年04期
相關(guān)博士學位論文 前7條
1 雷迎科;流形學習算法及其應(yīng)用研究[D];中國科學技術(shù)大學;2011年
2 詹宇斌;流形學習理論與方法及其應(yīng)用研究[D];國防科學技術(shù)大學;2011年
3 尹奎英;SAR圖像處理及地面目標識別技術(shù)研究[D];西安電子科技大學;2011年
4 咼維;城市地區(qū)高分辨率SAR圖像中典型地物的特征分析與解譯[D];武漢大學;2010年
5 楊國鵬;基于機器學習方法的高光譜影像分類研究[D];解放軍信息工程大學;2010年
6 王靖;流形學習的理論與方法研究[D];浙江大學;2006年
7 趙炳愛;基于小波分析的高分辨率雷達目標識別方法研究[D];哈爾濱工程大學;2003年
相關(guān)碩士學位論文 前7條
1 李雪薇;高分辨率SAR影像對象化的極化分解與特征描述研究[D];上海交通大學;2014年
2 孫晰銳;基于核學習的SAR圖像分類算法研究[D];大連理工大學;2012年
3 賀崢嶸;極化SAR影像特征分析與地物目標分類研究[D];解放軍信息工程大學;2011年
4 王濤;基于流形學習的SAR自動目標識別方法研究[D];電子科技大學;2010年
5 葉強;基于流形學習像素分布流的高光譜圖像數(shù)據(jù)分割方法[D];西安電子科技大學;2010年
6 丘昌鎮(zhèn);高分辨率SAR圖像目標分類特征提取與分析[D];國防科學技術(shù)大學;2009年
7 韓征;基于投影特征的SAR自動目標識別技術(shù)研究[D];中國民航大學;2009年
，本文編號：2160745
本文鏈接：http://www.sikaile.net/kejilunwen/dizhicehuilunwen/2160745.html
最近更新
教材專著
