本文關(guān)鍵詞： 高光譜圖像 端元提取 豐度估計(jì) LSE OSP OVP ATGP UOVP　出處：《大連海事大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：高光譜遙感數(shù)據(jù)由于具有空間和光譜的雙重信息,愈加廣泛地應(yīng)用在軍事、醫(yī)學(xué)、農(nóng)業(yè)以及公共安全等領(lǐng)域。但由于自然界中地物的復(fù)雜性以及高光譜圖像空間分辨率的限制使得每個(gè)像元包含了較多的物質(zhì)信息,導(dǎo)致大量混合像元的存在,從而增加了數(shù)據(jù)分析的難度,光譜解混技術(shù)可以定量地對(duì)地物屬性進(jìn)行描述。端元提取和豐度估計(jì)是高光譜解混技術(shù)中最重要的兩個(gè)主題。端元代表圖像中純粹的光譜特征,而豐度可以精確地分析混合像素的比重。在端元提取中,ATGP算法是提取端元的代表算法之一;在豐度估計(jì)中,LSE和OSP是最常用的兩種方法。但是傳統(tǒng)的算法,如ATGP、LSE和OSP的設(shè)計(jì)思路,通常具有過(guò)多的矩陣求逆和乘法運(yùn)算,使得它們?cè)谲浖䦟?shí)現(xiàn)時(shí)速度慢,在硬件上難以實(shí)現(xiàn)。因此,這些算法不能滿足許多應(yīng)用的實(shí)時(shí)需求,應(yīng)該尋找一種適合快速處理具有大量數(shù)據(jù)的遙感圖像的算法。豐度估計(jì)OVP算法和端元提取UOVP算法,其通過(guò)Gram-Schmidt正交化的思想進(jìn)行解混,不涉及任何矩陣求逆操作,更適合于并行計(jì)算。論文對(duì)上述幾種監(jiān)督式端豐度估計(jì)算法和非監(jiān)督式端元提取算法進(jìn)行研究,給出了基于GPU端設(shè)計(jì)方案,詳細(xì)工作如下:通過(guò)深入研究豐度估計(jì)的三種算法(LSE、OSP和OVP)和非監(jiān)督式端元提取算法(ATGP和UOVP)的設(shè)計(jì)思想,分別完成了基于GPU并行平臺(tái)的設(shè)計(jì)和CPU串行平臺(tái)的LSE、OSP、OVP、ATGP和UOVP算法的設(shè)計(jì),其中OVP算法分為CUDA架構(gòu)以及OpenMP+CUDA混合架構(gòu)兩種設(shè)計(jì)模式,并對(duì)各種算法的并行效果進(jìn)行比較和分析。分別在模擬高光譜圖像和真實(shí)高光譜圖像上進(jìn)行實(shí)驗(yàn),縱向比較了各個(gè)算法在GPU并行情況下和CPU串行情況下的時(shí)間性能;橫向比較了豐度估計(jì)三種算法和端元提取兩種算法在GPU平臺(tái)下的時(shí)間性能。從而驗(yàn)證OVP-GPU和UOVP-GPU并行設(shè)計(jì)的有效性,提高了高光譜解混的實(shí)時(shí)性。理論分析和實(shí)驗(yàn)結(jié)果表明,GPU并行設(shè)計(jì)可以很大幅度提高算法的運(yùn)行速度,能夠更好地滿足系統(tǒng)對(duì)實(shí)時(shí)性的要求,且豐度估計(jì)算法OVP和端元提取UOVP更適合GPU并行設(shè)計(jì)。
[Abstract]:Hyperspectral remote sensing data have been widely used in military and medical science because of the dual information of space and spectrum. However, due to the complexity of ground objects in nature and the limitation of spatial resolution of hyperspectral images, each pixel contains more material information, resulting in the existence of a large number of mixed pixels. Thus increasing the difficulty of data analysis. Spectral demultiplexing technique can be used to describe the properties of ground objects quantitatively. End-component extraction and abundance estimation are the two most important topics in hyperspectral demultiplexing technology. Endelements represent pure spectral features in images. The abundance can accurately analyze the specific gravity of the mixed pixels. The ATGP algorithm is one of the representative algorithms for the extraction of the end elements. LSE and OSP are the two most commonly used methods in abundance estimation, but the traditional algorithms, such as ATGP LSE and OSP, usually have too many matrix inverse and multiplication operations. These algorithms can not meet the real-time requirements of many applications because they are slow in software implementation and difficult to implement in hardware. We should find a suitable algorithm for fast processing remote sensing images with a large amount of data. The OVP algorithm of abundance estimation and the UOVP algorithm of End-element extraction should be found. It is unmixed by the idea of Gram-Schmidt orthogonalization, and does not involve any matrix inverse operation. It is more suitable for parallel computing. In this paper, several supervised end abundance estimation algorithms and unsupervised end component extraction algorithms are studied, and the design scheme based on GPU is given. The detailed work is as follows: the design ideas of LSEOSP and OVPs and unsupervised End-element extraction algorithms (ATGP and UOVPP) are studied in detail. The design of parallel platform based on GPU and the design of UOVP algorithm based on CPU serial platform are completed respectively. The OVP algorithm is divided into two design patterns: CUDA architecture and OpenMP CUDA hybrid architecture. The parallel effects of various algorithms are compared and analyzed. Experiments are carried out on simulated hyperspectral images and real hyperspectral images. The time performance of each algorithm in GPU parallel case and CPU serial case is compared longitudinally. The time performance of the three algorithms of abundance estimation and End-component extraction on GPU platform is compared in order to verify the effectiveness of OVP-GPU and UOVP-GPU parallel design. The theoretical analysis and experimental results show that the parallel design of GPU can greatly improve the speed of the algorithm, and can better meet the real-time requirements of the system. The abundance estimation algorithm OVP and End-component extraction UOVP are more suitable for GPU concurrent design.
【學(xué)位授予單位】：大連海事大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP751

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 宋梅萍;徐行偉;Chein-I Chang;安居白;Yao Li;;用于光譜解混的正交向量投影算法[J];光譜學(xué)與光譜分析;2015年12期

2 方凌江;粘永健;雷樹濤;倪志揚(yáng);;基于頂點(diǎn)成分分析的高光譜圖像端元提取算法[J];艦船電子工程;2014年08期

3 羅耀華;郭科;趙仕波;;基于GPU的高光譜遙感MNF并行方法研究[J];四川師范大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年03期

4 陳偉;余旭初;王鶴;;基于OSP的自動(dòng)端元提取及混合像元線性分解[J];測(cè)繪工程;2008年06期

5 耿修瑞,張兵,張霞,鄭蘭芬;一種基于高維空間凸面單形體體積的高光譜圖像解混算法[J];自然科學(xué)進(jìn)展;2004年07期

6 蘇燕玲,張瑞平;由施密特正交化法所得到的兩個(gè)結(jié)論[J];陜西師范大學(xué)學(xué)報(bào)(自然科學(xué)版);1999年S1期

相關(guān)博士學(xué)位論文 前1條

1 黃遠(yuǎn)程;高光譜影像混合像元分解的若干關(guān)鍵技術(shù)研究[D];武漢大學(xué);2010年

相關(guān)碩士學(xué)位論文 前5條

1 肖霄;基于正交投影理論的端元提取算法[D];大連海事大學(xué);2016年

2 葉舜;基于GPU的高光譜圖像混合像元分解并行優(yōu)化研究[D];南京理工大學(xué);2014年

3 趙進(jìn);基于GPU的遙感圖像并行處理算法及其優(yōu)化技術(shù)研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2011年

4 張晶;高光譜圖像解混技術(shù)研究[D];哈爾濱工程大學(xué);2011年

5 金晶;多/高光譜遙感圖像光譜分解研究與應(yīng)用[D];復(fù)旦大學(xué);2010年

，

本文編號(hào)：1458460