基于GPU的高光譜圖像混合像元分解并行優(yōu)化研究
發(fā)布時間：2019-05-03 18:55
【摘要】：高光譜遙感由于其較高空間分辨率和光譜分辨率的特點,被廣泛應(yīng)用于地球科學(xué)的各個領(lǐng)域。在整個高光譜圖像處理流程中,混合像元分解技術(shù)是其關(guān)鍵環(huán)節(jié)和研究熱點。但現(xiàn)有混合像元分解算法執(zhí)行效率低,無法滿足大數(shù)據(jù)量遙感圖像的實時處理需求,而GPU/CUDA架構(gòu)能夠為算法提供接近計算機集群的高計算能力,利用GPU高并行處理能力和高存儲帶寬的優(yōu)勢來提高混合像元分解算法的執(zhí)行效率是一種有效的研究思路。 針對上述科學(xué)問題,本文分析了高光譜遙感的成像機理與線性光譜混合模型,在研究并行計算發(fā)展現(xiàn)狀、GPGPU異構(gòu)編程模型和基于CUDA架構(gòu)的并行優(yōu)化模式的基礎(chǔ)上,結(jié)合GPU/CUDA架構(gòu),針對傳統(tǒng)高光譜混合像元分解和稀疏性高光譜混合像元分解進行了并行優(yōu)化處理。 首先,分析了傳統(tǒng)高光譜端元提取算法的基本原理,結(jié)合算法中對不同像元處理的不相關(guān)性,設(shè)計了基于GPU并行計算的PPI和N-FINDR端元提取算法。將傳統(tǒng)PPI算法中的向量投影問題轉(zhuǎn)換為矩陣相乘進行并行優(yōu)化,在保證精度的同時,取得了最高百倍的加速比；同時,提出了端元集并發(fā)替換方法對傳統(tǒng)N-FINDR算法進行優(yōu)化,也取得了顯著的加速比。 其次,對基于非負矩陣分解的高光譜混合像元分解方法進行了深入研究,針對其中代表性的約束非負矩陣分解算法,通過線程映射、存儲器優(yōu)化等方式設(shè)計其并行優(yōu)化方法,然后分別利用模擬和實際高光譜數(shù)據(jù)進行實驗測試分析,驗證了其有效性。 最后,研究了基于GPU的稀疏性高光譜圖像混合像元分解的并行優(yōu)化方法。為了滿足算法實時性的要求,針對基于L1/2范數(shù)的非負矩陣分解高光譜混合像元分解算法(L1/2NMF)中正則化約束高復(fù)雜度的問題,采用合理的任務(wù)分配,設(shè)計CPU+GPU異構(gòu)并行計算方法,顯著提高了算法處理速度。同時針對一種新稀疏性約束的非負矩陣分解高光譜混合像元分解算法(CSNMF),利用大規(guī)模線程并行計算技術(shù),結(jié)合算法原理進行了優(yōu)化設(shè)計與實現(xiàn),并在Telsa C2050平臺上進行了實驗測試,測試結(jié)果表明基于GPU的并行優(yōu)化方法能為高復(fù)雜度高精度的稀疏性高光譜圖像混合像元分解技術(shù)帶來極大的效率提升,為此類算法在實時性要求較高的遙感信息處理中應(yīng)用帶來可能。
[Abstract]:Hyperspectral remote sensing is widely used in various fields of earth science because of its high spatial resolution and spectral resolution. In the whole process of hyperspectral image processing, hybrid pixel decomposition is the key link and research focus. However, the existing hybrid pixel decomposition algorithms are inefficient and can not meet the real-time processing requirements of large amounts of remote sensing images. However, GPU/CUDA architecture can provide the algorithm with high computing power close to the cluster of computers. It is an effective research idea to improve the execution efficiency of hybrid pixel decomposition algorithm by using the advantages of high parallel processing ability and high memory bandwidth of GPU. In this paper, the imaging mechanism and linear spectral hybrid model of hyperspectral remote sensing are analyzed. On the basis of studying the development of parallel computing, GPGPU heterogeneous programming model and parallel optimization model based on CUDA architecture, this paper analyzes the imaging mechanism and linear spectral hybrid model of hyperspectral remote sensing. Combined with GPU/CUDA architecture, parallel optimization is carried out for traditional hyperspectral mixed pixel decomposition and sparse hyperspectral mixed pixel decomposition. Firstly, the basic principle of the traditional hyperspectral end element extraction algorithm is analyzed. Combined with the irrelevance of different pixel processing in the algorithm, the PPI and N-FINDR end element extraction algorithms based on GPU parallel computation are designed. The vector projection problem in the traditional PPI algorithm is transformed into matrix multiplication for parallel optimization. The precision is guaranteed and the acceleration ratio is up to 100 times. At the same time, an end-set concurrent replacement method is proposed to optimize the traditional N-FINDR algorithm, and a remarkable acceleration ratio is also obtained. Secondly, the hyperspectral mixed pixel decomposition method based on non-negative matrix decomposition is deeply studied. Aiming at the representative constrained non-negative matrix decomposition algorithm, the parallel optimization method is designed by thread mapping and memory optimization. Then the simulation and actual hyperspectral data are used to test and analyze the experimental results, and the validity of the proposed method is verified. Finally, the parallel optimization method of sparse hyperspectral image hybrid pixel decomposition based on GPU is studied. In order to meet the real-time requirements of the algorithm, a reasonable task allocation method is adopted to solve the problem of high complexity of regularization constraints in the non-negative matrix decomposition hyperspectral mixed pixel decomposition (L1/2NMF) algorithm based on L _ 1 ~ (2) ~ (2) norm. The CPU GPU heterogeneous parallel computing method is designed to improve the processing speed of the algorithm. At the same time, a new non-negative matrix decomposition hyperspectral mixed pixel decomposition algorithm (CSNMF),) with sparsity constraints is designed and implemented by using the massively threading parallel computing technology and combining with the algorithm principle. The experimental results on the Telsa C2050 platform show that the parallel optimization method based on GPU can greatly improve the efficiency of the high complexity and high precision hybrid pixel decomposition technique for sparse hyperspectral images, and the experimental results show that the parallel optimization method based on GPU can greatly improve the efficiency of the hybrid pixel decomposition technique for sparse and sparse hyperspectral images. It is possible for this algorithm to be used in remote sensing information processing with high real-time requirements.
【學(xué)位授予單位】：南京理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TP751
[Abstract]:Hyperspectral remote sensing is widely used in various fields of earth science because of its high spatial resolution and spectral resolution. In the whole process of hyperspectral image processing, hybrid pixel decomposition is the key link and research focus. However, the existing hybrid pixel decomposition algorithms are inefficient and can not meet the real-time processing requirements of large amounts of remote sensing images. However, GPU/CUDA architecture can provide the algorithm with high computing power close to the cluster of computers. It is an effective research idea to improve the execution efficiency of hybrid pixel decomposition algorithm by using the advantages of high parallel processing ability and high memory bandwidth of GPU. In this paper, the imaging mechanism and linear spectral hybrid model of hyperspectral remote sensing are analyzed. On the basis of studying the development of parallel computing, GPGPU heterogeneous programming model and parallel optimization model based on CUDA architecture, this paper analyzes the imaging mechanism and linear spectral hybrid model of hyperspectral remote sensing. Combined with GPU/CUDA architecture, parallel optimization is carried out for traditional hyperspectral mixed pixel decomposition and sparse hyperspectral mixed pixel decomposition. Firstly, the basic principle of the traditional hyperspectral end element extraction algorithm is analyzed. Combined with the irrelevance of different pixel processing in the algorithm, the PPI and N-FINDR end element extraction algorithms based on GPU parallel computation are designed. The vector projection problem in the traditional PPI algorithm is transformed into matrix multiplication for parallel optimization. The precision is guaranteed and the acceleration ratio is up to 100 times. At the same time, an end-set concurrent replacement method is proposed to optimize the traditional N-FINDR algorithm, and a remarkable acceleration ratio is also obtained. Secondly, the hyperspectral mixed pixel decomposition method based on non-negative matrix decomposition is deeply studied. Aiming at the representative constrained non-negative matrix decomposition algorithm, the parallel optimization method is designed by thread mapping and memory optimization. Then the simulation and actual hyperspectral data are used to test and analyze the experimental results, and the validity of the proposed method is verified. Finally, the parallel optimization method of sparse hyperspectral image hybrid pixel decomposition based on GPU is studied. In order to meet the real-time requirements of the algorithm, a reasonable task allocation method is adopted to solve the problem of high complexity of regularization constraints in the non-negative matrix decomposition hyperspectral mixed pixel decomposition (L1/2NMF) algorithm based on L _ 1 ~ (2) ~ (2) norm. The CPU GPU heterogeneous parallel computing method is designed to improve the processing speed of the algorithm. At the same time, a new non-negative matrix decomposition hyperspectral mixed pixel decomposition algorithm (CSNMF),) with sparsity constraints is designed and implemented by using the massively threading parallel computing technology and combining with the algorithm principle. The experimental results on the Telsa C2050 platform show that the parallel optimization method based on GPU can greatly improve the efficiency of the high complexity and high precision hybrid pixel decomposition technique for sparse hyperspectral images, and the experimental results show that the parallel optimization method based on GPU can greatly improve the efficiency of the hybrid pixel decomposition technique for sparse and sparse hyperspectral images. It is possible for this algorithm to be used in remote sensing information processing with high real-time requirements.
【學(xué)位授予單位】：南京理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TP751
【參考文獻】
相關(guān)期刊論文 前10條
1 陶欣;范聞捷;徐希孺;;高光譜數(shù)據(jù)組分信息的盲分解方法[J];北京大學(xué)學(xué)報(自然科學(xué)版)網(wǎng)絡(luò)版(預(yù)印本);2008年01期
2 陳偉;余旭初;劉偉;楊國鵬;;一種非監(jiān)督快速端元提取方法[J];測繪科學(xué);2009年05期
3 王立國;張晶;;基于線性光譜混合模型的光譜解混改進模型[J];光電子.激光;2010年08期
4 劉建軍;吳澤彬;韋志輝;肖亮;孫樂;;基于約束非負矩陣分解的高光譜圖像解混快速算法[J];電子學(xué)報;2013年03期
5 李二森;張振華;趙國青;宋麗華;;改進的MVC-NMF算法在高光譜圖像解混中的應(yīng)用[J];海洋測繪;2010年05期
6 翟艷堂;涂強;郎顯宇;陸忠華;遲學(xué)斌;;基于CUDA的蛋白質(zhì)翻譯后修飾鑒定MS-Alignment算法加速研究[J];計算機應(yīng)用研究;2010年09期
7 陳國良;孫廣中;徐云;龍柏;;并行計算的一體化研究現(xiàn)狀與發(fā)展趨勢[J];科學(xué)通報;2009年08期
8 劉赫男,羅霄,高曉東;并行計算的現(xiàn)狀與發(fā)展[J];煤;2001年01期
9 普晗曄;王斌;張立明;;基于Cayley-Menger行列式的高光譜遙感圖像端元提取方法[J];紅外與毫米波學(xué)報;2012年03期
10 賈森;錢l勌，
本文編號：2469183
本文鏈接：http://sikaile.net/guanlilunwen/gongchengguanli/2469183.html
最近更新
教材專著
