【摘要】：近年來(lái)，隨著遙感技術(shù)的迅猛發(fā)展，人們可以獲取大量的高光譜數(shù)據(jù)，，如何根據(jù)這些數(shù)據(jù)進(jìn)行準(zhǔn)確的地物分類，是遙感數(shù)據(jù)應(yīng)用水平提高的關(guān)鍵。目前已有大量機(jī)器學(xué)習(xí)算法用于高光譜數(shù)據(jù)的分類，這些方法基本上都基于聚類假設(shè)，即光譜相同/相似的數(shù)據(jù)具有相同/相似的標(biāo)簽。但是，由于傳感器噪聲以及成像設(shè)備分辨率的限制，實(shí)際高光譜數(shù)據(jù)中存在嚴(yán)重的“同物異譜”和“同譜異物”現(xiàn)象，嚴(yán)重制約了聚類假設(shè)下分類器的性能提高。針對(duì)這一問題，本文將松弛聚類假設(shè)思想引入到高光譜數(shù)據(jù)分類中，與稀疏編碼分類器和SVM(Support Vector Machine)分類器結(jié)合，發(fā)展了松弛聚類假設(shè)下的高光譜數(shù)據(jù)分類方法。主要研究工作和創(chuàng)新包括以下內(nèi)容： (1)設(shè)計(jì)了一種松弛聚類假設(shè)下的高光譜數(shù)據(jù)稀疏編碼分類算法。將松弛聚類假設(shè)思想以概率向量的形式應(yīng)用到稀疏編碼模型下，設(shè)計(jì)了相應(yīng)的優(yōu)化目標(biāo)函數(shù)與優(yōu)化算法。在實(shí)際高光譜數(shù)據(jù)集上進(jìn)行的仿真實(shí)驗(yàn)結(jié)果表明：松弛聚類假設(shè)能夠大大改善由于混合像元引起的數(shù)據(jù)分類正確率不高的情況。 (2)設(shè)計(jì)了一種松弛聚類假設(shè)下的半監(jiān)督高光譜數(shù)據(jù)分類算法(RCA-SLR-SSC)。該算法是將松弛聚類假設(shè)思想應(yīng)用到SVM分類器下，定義了松弛聚類假設(shè)下的半監(jiān)督圖Laplacian正則，以及根據(jù)高光譜數(shù)據(jù)的空間約束正則。松弛聚類假設(shè)思想降低了像元誤分的可能性，空間圖正則的加入增強(qiáng)了樣本標(biāo)記的平滑性，減少了樣本標(biāo)記中的奇異點(diǎn)。所以，該算法能夠得到較高的分類正確率。在實(shí)際高光譜數(shù)據(jù)集上進(jìn)行的仿真實(shí)驗(yàn)驗(yàn)證了該算法的性能。與同類算法相比，該算法能夠在較少樣本情況下得到較好的分類結(jié)果。 (3)設(shè)計(jì)了一種空-譜松弛聚類假設(shè)下的半監(jiān)督高光譜圖像分類方法。該算法是對(duì)RCA-SLR-SSC算法在空間上進(jìn)行了進(jìn)一步松弛。即利用sketch算法提取出高光譜數(shù)據(jù)中背景像元與待分類像元之間邊界處的像元，并減小這些像元對(duì)應(yīng)的空間約束矩陣中的權(quán)值，構(gòu)造一個(gè)新的拉普拉斯圖矩陣。再將這個(gè)新的拉普拉斯圖矩陣應(yīng)用到RCA-SLR-SSC算法中。松弛聚類假設(shè)思想在空間上的應(yīng)用大大降低了因空間約束而造成的邊界處像元的誤分，提高了分類正確率。高光譜數(shù)據(jù)集上的仿真實(shí)驗(yàn)也表明：與RCA-SLR-SSC算法相比，該算法在邊界處像元的分類上具有明顯的優(yōu)越性。
[Abstract]:In recent years, with the rapid development of remote sensing technology, people can obtain a large number of hyperspectral data. How to classify objects accurately based on these data is the key to improve the application level of remote sensing data. At present, a large number of machine learning algorithms have been applied to the classification of hyperspectral data. These methods are based on the clustering assumption that the data with the same spectrum / similar spectrum have the same / similar labels. However, due to the limitation of sensor noise and resolution of imaging equipment, there are serious phenomena of "isomorphism" and "isospectral foreign body" in the actual hyperspectral data, which seriously restrict the performance improvement of the classifier under clustering assumption. To solve this problem, this paper introduces the idea of relaxation clustering hypothesis into hyperspectral data classification, and combines with sparse coding classifier and SVM (Support Vector Machine) classifier to develop the hyperspectral data classification method under relaxed clustering assumption. The main research work and innovations are as follows: (1) A sparse coding algorithm for hyperspectral data under relaxed clustering assumption is designed. The relaxation clustering hypothesis is applied to the sparse coding model in the form of probability vector, and the corresponding optimization objective function and optimization algorithm are designed. The simulation results on the actual hyperspectral data set show that the relaxed clustering assumption can greatly improve the low accuracy of data classification caused by mixed pixels. (2) A semi-supervised hyperspectral data classification algorithm (RCA-SLR-SSC) under relaxed clustering assumption is designed. In this algorithm, the relaxation clustering hypothesis is applied to the SVM classifier, and the semi-supervised graph Laplacian canonical under the relaxed clustering assumption is defined, as well as the spatially constrained regularization based on hyperspectral data. The loose clustering hypothesis reduces the possibility of pixel misdivision, and the addition of regular space graph enhances the smoothness of the sample marking and reduces the singularity in the sample marking. Therefore, the algorithm can achieve a higher classification accuracy. The performance of the algorithm is verified by simulation on the actual hyperspectral data set. Compared with similar algorithms, this algorithm can obtain better classification results with fewer samples. (3) A semi-supervised hyperspectral image classification method under the assumption of space-spectrum relaxation clustering is designed. The algorithm further relaxes the RCA-SLR-SSC algorithm in space. The algorithm of sketch is used to extract the pixels at the boundary between the background pixel and the pixel to be classified in hyperspectral data, and to reduce the weights in the spatial constraint matrix corresponding to these pixels, and to construct a new Laplace map matrix. Then the new Laplace matrix is applied to RCA-SLR-SSC algorithm. The application of relaxation clustering hypothesis in space greatly reduces the misclassification of pixels at the boundary caused by spatial constraints and improves the classification accuracy. The simulation results on the hyperspectral data set also show that the proposed algorithm is superior to the RCA-SLR-SSC algorithm in the classification of pixels at the boundary.
【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
【分類號(hào)】：TP751

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 楊哲海,韓建峰,宮大鵬,李之歆;高光譜遙感技術(shù)的發(fā)展與應(yīng)用[J];海洋測(cè)繪;2003年06期

2 陳進(jìn);王潤(rùn)生;;高斯最大似然分類在高光譜分類中的應(yīng)用研究[J];計(jì)算機(jī)應(yīng)用;2006年08期

3 高恒振;萬(wàn)建偉;徐湛;錢林杰;;基于光譜加權(quán)直推式支持向量機(jī)的高光譜圖像半監(jiān)督分類[J];信號(hào)處理;2011年01期

相關(guān)博士學(xué)位論文 前2條

1 陳進(jìn);高光譜圖像分類方法研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2010年

2 崔燕;光譜成像儀定標(biāo)技術(shù)研究[D];中國(guó)科學(xué)院研究生院（西安光學(xué)精密機(jī)械研究所）;2009年

本文編號(hào)：2351149