本文選題：高光譜影像分類 + 云計(jì)算��； 參考：《福建師范大學(xué)》2014年博士論文

【摘要】：高光譜遙感影像具有波段多、數(shù)據(jù)量大、數(shù)據(jù)不確定性和監(jiān)督分類時(shí)易受Hughes現(xiàn)象影響等特點(diǎn),由此對(duì)現(xiàn)有的圖像信息分析處理技術(shù)提出了更高的要求。支持向量機(jī)(SVM)是一種基于統(tǒng)計(jì)學(xué)習(xí)理論且已被眾多實(shí)驗(yàn)所證實(shí)的有效學(xué)習(xí)機(jī)制,能較好地解決小樣本、非線性、高維數(shù)等問題,并已被成功地應(yīng)用于高光譜分類領(lǐng)域；但對(duì)于大規(guī)模高光譜影像的分類問題,SVM傳統(tǒng)算法(串行)的訓(xùn)練和預(yù)測(cè)效率低下,而單機(jī)和傳統(tǒng)分布式環(huán)境也難以提供處理海量數(shù)據(jù)所需的強(qiáng)大并行運(yùn)算能力和足夠的內(nèi)存空間。有鑒于此,本文引入并行支持向量機(jī)(PSVM)和云計(jì)算技術(shù),設(shè)計(jì)出一種基于云計(jì)算的并行支持向量機(jī)(Cloud-PSVM)分類模型,提出云環(huán)境下Cloud-PSVM的增量學(xué)習(xí)算法和參數(shù)的全局優(yōu)化策略,并將Cloud-PSVM應(yīng)用于土地利用分類領(lǐng)域,構(gòu)建基于Hadoop平臺(tái)的高光譜影像分類云服務(wù)。整個(gè)研究從計(jì)算模式、分類方法和服務(wù)模式這三方面入手,旨在保證分類精度的前提下提高高光譜影像分類的效率,推動(dòng)大規(guī)模高光譜影像地物信息提取與機(jī)器解譯的規(guī)�；椭悄芑Ｖ饕芯�?jī)?nèi)容與成果如下： (1)為有效地提高Hyperion高光譜影像的空間分辨率,設(shè)計(jì)出一種改進(jìn)型的Gram-Schmidt高光譜影像融合方法,實(shí)現(xiàn)了Hyperion高光譜影像與同一遙感平臺(tái)及同一時(shí)相的ALI高空間分辨率影像的高效融合；提出一種基于光譜-地形,以及紋理特征的組合徑向基核函數(shù)(MRBF),并構(gòu)建出一種基于MRBF的二叉決策樹多類SMO (BDT-SMO)分類器,可有效地提高高光譜融合影像的分類精度。 (2)構(gòu)建Hadoop云儲(chǔ)存平臺(tái),采用Hadoop分布式文件系統(tǒng)(HDFS)和Hbase數(shù)據(jù)庫(kù)實(shí)現(xiàn)大規(guī)模高光譜融合影像數(shù)據(jù)和樣本數(shù)據(jù)的分布式存儲(chǔ),通過合理選擇分割策略、存取機(jī)制和數(shù)據(jù)組織形式,可有效地提高大規(guī)模融合影像和樣本數(shù)據(jù)的存取效率。 (3)為有效地提高大規(guī)模訓(xùn)練樣本的并行學(xué)習(xí)效率,提出一種基于交叉樣本的改進(jìn)型混合并行支持向量機(jī)(YBJCF-PSVM)模型,并與GPU技術(shù)相結(jié)合,以提高單節(jié)點(diǎn)的并行學(xué)習(xí)能力。此外,設(shè)計(jì)出一種基于MapReduce和YBJCF-PSVM模式的Cloud-PSVM分類器。 (4)將Cloud-PSVM應(yīng)用于土地利用分類領(lǐng)域。采用MapReduce模式對(duì)實(shí)驗(yàn)區(qū)高光譜融合影像進(jìn)行并行特征提取,并通過Cloud-PSVM分類器對(duì)大規(guī)模樣本進(jìn)行并行訓(xùn)練與預(yù)測(cè)。實(shí)驗(yàn)結(jié)果表明,Cloud-PSVM分類器能在保證分類精度的前提下較大程度地提高高光譜融合影像的分類效率。此外,為能有效地提高土地利用分類結(jié)果的發(fā)布效率,還設(shè)計(jì)并實(shí)現(xiàn)了一種基于Hadoop的高光譜融合影像分類的云服務(wù)。 (5)在云計(jì)算環(huán)境下設(shè)計(jì)出一種基于MapReduce和殼向量的SVM增量學(xué)習(xí)算法(MapReduce-HASVM),可有效地提高Cloud-PSVM分類器的泛化能力和擴(kuò)展性。此外,還提出一種基于云計(jì)算和并行遺傳算法(PGA)的Cloud-PSVM參數(shù)分布式全局優(yōu)化策略,可有效地提高Cloud-PSVM分類器的分類精度和核參數(shù)的優(yōu)化效率。
[Abstract]:Hyperspectral remote sensing images have many characteristics such as multi band, large amount of data, uncertainty of data and the influence of Hughes phenomenon when supervised classification. Thus, higher requirements are put forward for the existing image information analysis and processing technology. Support vector machine (SVM) is an effective learning mechanism based on statistical theory and has been proved by many experiments. It can solve the problems of small sample, nonlinear, high dimensional number and so on, and has been successfully applied to the hyperspectral classification field. But for the classification of large-scale hyperspectral images, the training and prediction efficiency of the traditional SVM algorithm (serial) is low, while the single machine and the traditional distributed environment are also difficult to provide the powerful parallel processing of massive data. In view of this, this paper introduces a parallel support vector machine (PSVM) and cloud computing technology to design a parallel support vector machine (Cloud-PSVM) classification model based on cloud computing, and proposes a global optimization strategy for incremental learning algorithms and parameters of Cloud-PSVM in the cloud environment, and applies Cloud-PSVM to the land. The Hadoop Platform Based Hyperspectral Image Classification cloud service based on the classification field is constructed. The whole study starts with the three aspects of the computing mode, the classification method and the service mode. The purpose is to improve the efficiency of the hyperspectral image classification under the premise of guaranteeing the classification accuracy, and promote the scale of the large-scale high spectral image information extraction and the machine interpretation. The main research contents and results are as follows:
(1) in order to effectively improve the spatial resolution of Hyperion hyperspectral images, an improved Gram-Schmidt hyperspectral image fusion method is designed, which realizes the efficient fusion of Hyperion hyperspectral images with the same remote sensing platform and ALI high spatial resolution images in the same phase, and proposes a kind of spectral terrain and texture features. Combined radial basis kernel function (MRBF), and a MRBF based two fork decision tree multi class SMO (BDT-SMO) classifier, which can effectively improve the classification accuracy of hyperspectral fusion images.
(2) constructing the Hadoop cloud storage platform, using the Hadoop distributed file system (HDFS) and the Hbase database to realize the large-scale hyperspectral fusion image data and the distributed storage of the sample data. Through the rational selection of the segmentation strategy, the access mechanism and the data organization form, the access efficiency of the large-scale fusion image and the sample data can be effectively improved.
(3) in order to effectively improve the parallel learning efficiency of large-scale training samples, an improved hybrid parallel support vector machine (YBJCF-PSVM) model based on cross samples is proposed and combined with GPU technology to improve the parallel learning ability of single node. In addition, a Cloud-PSVM classifier based on MapReduce and YBJCF-PSVM mode is designed.
(4) Cloud-PSVM is applied to the field of land use classification. The MapReduce model is used to carry out parallel feature extraction for hyperspectral fusion images in the experimentation area, and the large-scale samples are trained and predicted by the Cloud-PSVM classifier. The experimental results show that the Cloud-PSVM classifier can greatly improve the classification accuracy. In addition, in order to effectively improve the efficiency of the distribution of land use classification results, a cloud service based on Hadoop Based Hyperspectral fusion image classification is also designed and implemented.
(5) a SVM incremental learning algorithm (MapReduce-HASVM) based on MapReduce and shell vector is designed under the cloud computing environment, which can effectively improve the generalization ability and extensibility of the Cloud-PSVM classifier. In addition, a distributed global optimization strategy for Cloud-PSVM parameters based on cloud computing and parallel genetic algorithm (PGA) is proposed, which can be effectively proposed. Classification accuracy and optimization efficiency of kernel parameters for high Cloud-PSVM classifier.
【學(xué)位授予單位】：福建師范大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP751

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 梁繼;王建;;Hyperion高光譜影像的分析與處理[J];冰川凍土;2009年02期

2 馮建輝;楊玉靜;;基于灰度共生矩陣提取紋理特征圖像的研究[J];北京測(cè)繪;2007年03期

3 阿布都瓦斯提·吾拉木,秦其明,朱黎江;基于6S模型的可見光、近紅外遙感數(shù)據(jù)的大氣校正[J];北京大學(xué)學(xué)報(bào)(自然科學(xué)版);2004年04期

4 林茂六;陳春雨;;基于傅立葉核與徑向基核的支持向量機(jī)性能之比較[J];重慶郵電學(xué)院學(xué)報(bào)(自然科學(xué)版);2005年06期

5 林繼鵬,劉君華,凌振寶;并行支持向量機(jī)算法及其應(yīng)用[J];吉林大學(xué)學(xué)報(bào)(信息科學(xué)版);2004年05期

6 杜培軍;林卉;孫敦新;;基于支持向量機(jī)的高光譜遙感分類進(jìn)展[J];測(cè)繪通報(bào);2006年12期

7 劉志剛,秦前清,李德仁,王新洲;基于混合核函數(shù)的支撐向量機(jī)及其在遙感影像土地利用分類中的應(yīng)用[J];測(cè)繪信息與工程;2003年05期

8 王晉川;何宏;張福臨;;MapReduce框架與調(diào)度容錯(cuò)機(jī)制研究[J];中國(guó)儲(chǔ)運(yùn);2010年12期

9 姜紅艷;邢立新;梁立恒;王明常;;PanSharpening自動(dòng)融合算法及應(yīng)用研究[J];測(cè)繪與空間地理信息;2008年05期

10 周清;祝民強(qiáng);;EO-1Hyperion高光譜數(shù)據(jù)FLAASH模塊大氣糾正及評(píng)價(jià)[J];測(cè)繪與空間地理信息;2011年06期

相關(guān)博士學(xué)位論文 前3條

1 康俊鋒;云計(jì)算環(huán)境下高分辨率遙感影像存儲(chǔ)與高效管理技術(shù)研究[D];浙江大學(xué);2011年

2 方雷;基于云計(jì)算的土地資源服務(wù)高效處理平臺(tái)關(guān)鍵技術(shù)探索與研究[D];浙江大學(xué);2011年

3 譚琨;基于支持向量機(jī)的高光譜遙感影像分類研究[D];中國(guó)礦業(yè)大學(xué);2010年

，

本文編號(hào)：1990831