本文關(guān)鍵詞： SAR圖像變化檢測(cè) 核模糊C均值 Hadoop Spark　出處：《西安電子科技大學(xué)》2014年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：SAR(Synthetic Aperture Radar)圖像變化檢測(cè)可以應(yīng)用在自然環(huán)境監(jiān)測(cè)、災(zāi)害評(píng)估、軍事打擊效果評(píng)估和城市規(guī)劃等眾多領(lǐng)域,使得SAR圖像變化檢測(cè)成為遙感領(lǐng)域的研究熱點(diǎn)。近年來(lái)隨著雷達(dá)成像能力的提升,SAR圖像的數(shù)據(jù)規(guī)模變得越來(lái)越大,傳統(tǒng)串行變化檢測(cè)算法已經(jīng)越來(lái)越難以應(yīng)對(duì)數(shù)據(jù)量不斷增長(zhǎng)的SAR圖像。本文將核模糊C均值聚類(lèi)算法(Kernel Fuzzy C-Means,KFCM)與分布式并行計(jì)算框架相結(jié)合,提出了兩種基于分布式并行聚類(lèi)的SAR圖像變化檢測(cè)方法,分布式并行計(jì)算框架能夠充分利用集群中眾多節(jié)點(diǎn)的計(jì)算能力和存儲(chǔ)能力,可以有效應(yīng)對(duì)大規(guī)模的SAR圖像變化檢測(cè)問(wèn)題,加快變化檢測(cè)的速度。1.提出了一種基于H-KFCM(Hadoop based KFCM)的分布式并行SAR圖像變化檢測(cè)方法。在變化檢測(cè)過(guò)程中,利用聚類(lèi)算法對(duì)差異圖進(jìn)行聚類(lèi)分析是計(jì)算復(fù)雜度最高,計(jì)算時(shí)間最長(zhǎng)的部分。Hadoop分布式集群計(jì)算平臺(tái)可以利用分布式文件系統(tǒng)HDFS(Hadoop Distributed File System)和Map Reduce計(jì)算模型分布式地存儲(chǔ)和處理大規(guī)模數(shù)據(jù)。本文提出的基于H-KFCM的SAR圖像變化檢測(cè)方法,將KFCM算法與Hadoop相結(jié)合,將KFCM算法中隸屬度迭代計(jì)算映射到Map Reduce中的Map階段,通過(guò)集群多節(jié)點(diǎn)分布式執(zhí)行Map任務(wù)實(shí)現(xiàn)隸屬度矩陣的并行計(jì)算;將KFCM的聚類(lèi)中心更新過(guò)程映射到Reduce階段,Reduce收集不同節(jié)點(diǎn)的Map任務(wù)計(jì)算結(jié)果,規(guī)約求和更新聚類(lèi)中心,實(shí)現(xiàn)了對(duì)SAR圖像變化檢測(cè)差異圖的分布式并行聚類(lèi)。通過(guò)設(shè)計(jì)相關(guān)實(shí)驗(yàn),證明了本文提出的H-KFCM分布式并行變化檢測(cè)方法是有效的,并且在Hadoop集群節(jié)點(diǎn)數(shù)增加時(shí),對(duì)相同SAR圖像的變化檢測(cè)時(shí)間明顯減少,證明了該算法具有良好的并行加速性能。2.提出了一種基于S-KFCM(Spark based KFCM)的SAR圖像變化檢測(cè)方法。Spark是一種針對(duì)迭代作業(yè)和交互分析等領(lǐng)域而設(shè)計(jì)的基于內(nèi)存計(jì)算的分布式并行平臺(tái),相比于Hadoop的Map Reduce框架,Spark在運(yùn)行相同的作業(yè)時(shí)可以取得幾十倍甚至百倍加速性能提升。該算法將利用KFCM算法分析差異圖的過(guò)程遷移到Spark內(nèi)存計(jì)算框架上實(shí)現(xiàn),將變化檢測(cè)過(guò)程中最耗時(shí)的聚類(lèi)分析過(guò)程并行的完成。在Spark中,KFCM算法的計(jì)算過(guò)程由一系列有依賴(lài)關(guān)系的彈性分布式數(shù)據(jù)集(Resilient Distributed Datasets,RDD)實(shí)現(xiàn),Spark能夠在集群多個(gè)節(jié)點(diǎn)上對(duì)RDD進(jìn)行并行計(jì)算。KFCM迭代過(guò)程需要重復(fù)地利用輸入數(shù)據(jù)集,RDD能夠?qū)⑦@些復(fù)用數(shù)據(jù)集駐留在內(nèi)存中,避免頻繁的硬盤(pán)I/O,提高了計(jì)算效率。通過(guò)在不同規(guī)模SAR圖像數(shù)據(jù)集上的實(shí)驗(yàn),結(jié)果證明基于S-KFCM的變化檢測(cè)方法是有效的,且相比基于Hadoop實(shí)現(xiàn)的變化檢測(cè)方法,該方法能達(dá)到17倍左右的加速性能,證明了該方法能夠支持大規(guī)模SAR圖像數(shù)據(jù)的聚類(lèi)分析,快速有效的完成SAR圖像變化檢測(cè)。
[Abstract]:SAR(Synthetic Aperture Radar-based image change detection can be used in many fields, such as natural environment monitoring, disaster assessment, military strike effect evaluation and urban planning, etc. In recent years, with the improvement of radar imaging ability, the data scale of SAR image becomes larger and larger. The traditional serial change detection algorithm has become more and more difficult to cope with the growing data volume of SAR images. In this paper, Kernel Fuzzy C-Meansn KFCM-based clustering algorithm is combined with distributed parallel computing framework. Two SAR image change detection methods based on distributed parallel clustering are proposed. The distributed parallel computing framework can make full use of the computing power and storage capacity of many nodes in the cluster. It can effectively deal with the problem of large-scale SAR image change detection, and accelerate the speed of change detection. 1. A distributed parallel SAR image change detection method based on H-KFCM-Hadoop based KFCM is proposed. Using clustering algorithm to cluster analysis of difference map is the highest computational complexity. The longest computing time. Hadoop distributed cluster computing platform can use distributed file system HDFS(Hadoop Distributed File system) and Map Reduce computing model to store and process large-scale data distributed. This paper proposes a SAR image change detection method based on H-KFCM. The KFCM algorithm is combined with Hadoop, and the iterative calculation of membership degree in KFCM algorithm is mapped to the Map stage in Map Reduce. The parallel computation of membership matrix is implemented by cluster multi-node distributed execution of Map task. The update process of KFCM cluster center is mapped to the Map task calculation result of different nodes collected by reduce in Reduce stage, and the clustering center is updated by protocol summation. The distributed parallel clustering of SAR image change detection difference graph is realized. It is proved that the H-KFCM distributed parallel change detection method proposed in this paper is effective, and when the number of Hadoop cluster nodes increases, the change detection time for the same SAR image is obviously reduced. It is proved that the algorithm has good parallel acceleration performance. 2. A SAR image change detection method based on S-KFCM-Spark based KFCM is proposed. Spark is a distributed parallel platform based on memory computing, which is designed for iterative operation and interactive analysis. Compared with Hadoop's Map Reduce framework, Spark can achieve a performance improvement of tens or even a hundredfold when running the same job. The algorithm migrates the process of analyzing difference graph using KFCM algorithm to Spark memory computing framework. Parallel completion of the most time-consuming clustering analysis process in the change detection process. In Spark, the KFCM algorithm is computed by a series of resilient Distributed data sets resilience data sets (RDDD), which can be implemented on multiple node pairs in a cluster. The RDD parallel computation. KFCM iteration process requires repeated use of input data sets to enable these multiplexed datasets to reside in memory, Through experiments on different scale SAR image data sets, the results show that the change detection method based on S-KFCM is effective and compared with the change detection method based on Hadoop. This method can achieve about 17 times the acceleration performance. It is proved that this method can support the clustering analysis of large scale SAR image data and can quickly and effectively complete the change detection of SAR images.
【學(xué)位授予單位】：西安電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：TN957.52

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 唐德可,付琨,王宏琦;基于光譜和空域信息的城區(qū)變化檢測(cè)方法研究[J];測(cè)繪科學(xué);2005年06期

2 吳華;常艷玲;沙瑞;;基于Laplacian Eigenmap的圖像變化檢測(cè)虛警優(yōu)化技術(shù)[J];計(jì)算機(jī)工程與應(yīng)用;2007年32期

3 李雪;舒寧;王琰;;利用向量相似性進(jìn)行基于像斑的土地利用變化檢測(cè)[J];遙感信息;2009年06期

4 李芳芳;肖本林;張謙;;基于改進(jìn)獨(dú)立分量分析的濕地變化檢測(cè)方法[J];計(jì)算機(jī)應(yīng)用;2010年05期

5 廖明生,朱攀,龔健雅;基于典型相關(guān)分析的多元變化檢測(cè)[J];遙感學(xué)報(bào);2000年03期

6 陳濤;郁文賢;粟毅;蔣詠梅;;基于生物視覺(jué)原理的圖像結(jié)構(gòu)信息變化檢測(cè)方法[J];國(guó)防科技大學(xué)學(xué)報(bào);2006年04期

7 宋妍;袁修孝;付迎春;;基于混合高斯密度模型和空間上下文信息的遙感影像變化檢測(cè)方法及擴(kuò)展[J];遙感學(xué)報(bào);2009年01期

8 王文杰;趙忠明;朱海青;;面向?qū)ο筇卣魅诤系母叻直媛蔬b感圖像變化檢測(cè)方法[J];計(jì)算機(jī)應(yīng)用研究;2009年08期

9 唐樸謙;楊建宇;張超;朱德海;蘇偉;;基于像素比值的面向?qū)ο蠓诸?lèi)后遙感變化檢測(cè)方法[J];遙感信息;2010年01期

10 李曉光;宋寶燕;張昕;;基于滑動(dòng)多窗口的時(shí)間序列流趨勢(shì)變化檢測(cè)[J];電子學(xué)報(bào);2010年02期

相關(guān)會(huì)議論文 前10條

1 尤紅建;詹芊芊;;尺度優(yōu)化的星載SAR圖像變化檢測(cè)[A];中國(guó)測(cè)繪學(xué)會(huì)第九次全國(guó)會(huì)員代表大會(huì)暨學(xué)會(huì)成立50周年紀(jì)念大會(huì)論文集[C];2009年

2 劉元波;;環(huán)境遙感變化探測(cè)研究中的若干問(wèn)題：輻射校正方法與變化檢測(cè)算法及其理論關(guān)系[A];中國(guó)地理學(xué)會(huì)2007年學(xué)術(shù)年會(huì)論文摘要集[C];2007年

3 邢帥;徐青;;高分辨率衛(wèi)星遙感影像變化檢測(cè)技術(shù)的研究[A];第十三屆全國(guó)圖象圖形學(xué)學(xué)術(shù)會(huì)議論文集[C];2006年

4 霍春雷;程健;周志鑫;盧漢清;;基于尺度傳播的多尺度變化檢測(cè)新方法[A];第十四屆全國(guó)圖象圖形學(xué)學(xué)術(shù)會(huì)議論文集[C];2008年

5 張蔚然;韓萍;;基于去取向理論的極化SAR變化檢測(cè)[A];第二十五屆中國(guó)（天津）2011’IT、網(wǎng)絡(luò)、信息技術(shù)、電子、儀器儀表創(chuàng)新學(xué)術(shù)會(huì)議論文集[C];2011年

6 胡艷;李勝;何宗;羅靈軍;李靜;;水體變化檢測(cè)在重慶市干旱遙感監(jiān)測(cè)中的應(yīng)用[A];重慶市測(cè)繪學(xué)會(huì)第三屆優(yōu)秀論文評(píng)選獲獎(jiǎng)?wù)撐聂?005-2006年度學(xué)術(shù)交流會(huì)論文選編[C];2008年

7 張鐵軍;;年度土地利用變更調(diào)查中遙感監(jiān)測(cè)圖斑提取方法淺析[A];福建省土地學(xué)會(huì)2012年年會(huì)論文集[C];2012年

8 柳思聰;杜培軍;;基于形態(tài)學(xué)濾波的多時(shí)相遙感影像變化檢測(cè)方法研究[A];第十七屆中國(guó)遙感大會(huì)摘要集[C];2010年

9 劉志剛;李夕海;錢(qián)昌松;;遙感圖像變化檢測(cè)問(wèn)題淺析[A];陜西地球物理文集（五）國(guó)家安全與軍事地球物理研究[C];2005年

10 劉翔;李萬(wàn)茂;高連如;陶發(fā)達(dá);倪金生;;基于遙感圖像變化檢測(cè)的投資項(xiàng)目搜索技術(shù)研究[A];中國(guó)遙感應(yīng)用協(xié)會(huì)2010年會(huì)暨區(qū)域遙感發(fā)展與產(chǎn)業(yè)高層論壇論文集[C];2010年

，

本文編號(hào)：1498705