改進(jìn)的經(jīng)驗(yàn)?zāi)B(tài)分解算法及其在高光譜圖像分類中的應(yīng)用
發(fā)布時(shí)間：2018-09-04 09:08
【摘要】：源于20世紀(jì)80年代的高光譜,是遙感技術(shù)的一大飛躍。與傳統(tǒng)可見光或多光譜圖像相比,高光譜圖像能提供更為豐富的地表覆蓋信息和地物光譜信息,在航天和軍事等領(lǐng)域具有很大潛力,因而受到國內(nèi)外學(xué)者的極大關(guān)注,成為目前的一個(gè)研究熱點(diǎn)。然而,如何遵循高光譜數(shù)據(jù)“非線性”、“非平穩(wěn)”的本質(zhì),充分利用采集到的圖像信息,以此提高地物分類識(shí)別的能力,成為高光譜遙感技術(shù)推廣和應(yīng)用道路上亟待解決的難題。雖然近年來發(fā)展起來的經(jīng)驗(yàn)?zāi)B(tài)分解算法(Empirical Mode Decomposition,EMD)對(duì)處理復(fù)雜的“非線性”、“非平穩(wěn)”高光譜數(shù)據(jù)具有先天優(yōu)勢(shì),但迄今為止尚無一套完整的、公認(rèn)的理論基礎(chǔ)。因此,如何從理論上對(duì)EMD進(jìn)行改進(jìn),尤其是端點(diǎn)效應(yīng)的抑制和包絡(luò)求取時(shí)的“上沖”或“下沖”現(xiàn)象的消除等,仍然是擺在研究者們面前的重大挑戰(zhàn)。本文圍繞EMD算法的理論改進(jìn)及其在高光譜圖像分類中的應(yīng)用展開深入細(xì)致的研究。一方面,基于灰色模型和最優(yōu)化理論,從端點(diǎn)效應(yīng)抑制和包絡(luò)求取等方面對(duì)EMD進(jìn)行改進(jìn),并將改進(jìn)的EMD用于高光譜地物譜線和空間特征提取;另一方面,基于稀疏表示分類器(Sparse RepresentationClassifier,SRC)和超像素圖像分割算法,研究譜-空間特征相結(jié)合的高光譜圖像分類方法。本文的主要研究?jī)?nèi)容和創(chuàng)新成果如下:研究基于單變量灰色模型的一維EMD(Gray Mode-based EMD,GM-EMD)端點(diǎn)效應(yīng)抑制方法。端點(diǎn)效應(yīng)是EMD算法中的公開理論問題,它是由于信號(hào)兩端附近極值點(diǎn)無法被準(zhǔn)確確定而產(chǎn)生的。本文先證明極值點(diǎn)和包絡(luò)對(duì)一維EMD至關(guān)重要,然后在微分方程離散化過程中對(duì)現(xiàn)有單變量灰色模型進(jìn)行了改進(jìn),提出GM-EMD方法,在不改變?cè)夹盘?hào)特性的前提下,充分發(fā)揮單變量灰色模型適合少量數(shù)據(jù)預(yù)測(cè)、計(jì)算量小和短期預(yù)測(cè)精度高等優(yōu)勢(shì),對(duì)一維EMD迭代過程中的信號(hào)向外延拓2個(gè)點(diǎn),有效抑制一維EMD的端點(diǎn)效應(yīng)。研究基于交替方向乘子法(Alternating Direction Method of Multipliers,ADMM)的一維EMD包絡(luò)求取方法。由于樣條插值過程中未對(duì)非極值點(diǎn)位置上的信號(hào)進(jìn)行約束,容易造成“上沖”或“下沖”現(xiàn)象。于是,構(gòu)建上、下包絡(luò)應(yīng)滿足的嚴(yán)格數(shù)學(xué)不等式,用ADMM來求解這些最優(yōu)化問題,與樣條插值相比,能有效消除“上沖”或“下沖”現(xiàn)象,得到更準(zhǔn)確的分解結(jié)果。研究基于多變量灰色模型的二維EMD(Gray Mode-based Bi-dimensionalEMD,GM-BEMD)端點(diǎn)效應(yīng)抑制算法。由于圖像邊界處極值點(diǎn)無法被準(zhǔn)確求取,造成了二維EMD(Bi-dimensional EMD,BEMD)的端點(diǎn)效應(yīng)問題。于是,提出GM-BEMD方法,該方法由基于復(fù)化Simpson公式的多變量灰色模型將圖像向四周延拓,再用傳統(tǒng)的BEMD方法對(duì)延拓后的圖像進(jìn)行分解,得到延拓的二維本征模態(tài)函數(shù)(Bi-dimensional Intrinsic Mode Function,BIMF)和殘差,然后截取出與原始圖像區(qū)域相對(duì)應(yīng)的分解結(jié)果,從而抑制BEMD端點(diǎn)效應(yīng)。研究基于核稀疏多任務(wù)學(xué)習(xí)(Kernel-based Sparse Multitask Learning Classi-fier,KSMTLC)的譜-空間特征分類方法。在SRC的框架下,提出用KSMTLC來綜合利用高光譜譜-空間特征,所涉及的最優(yōu)化問題由加速近端梯度法(Accelerated Proximal Gradient,APG)求解。與單一的光譜或空間特征相比,KSMTLC的分類效果更好。研究基于支持向量機(jī)(Support Vector Machine,SVM)和超像素圖像分割的譜-空間特征分類方法。先利用光譜特征得到高光譜的初步分類結(jié)果,再通過后處理的方式利用空間特征對(duì)初步分類結(jié)果進(jìn)行修正,從而得到最終的譜-空間特征分類結(jié)果。其中,初步分類結(jié)果由SVM對(duì)光譜特征進(jìn)行分類得到,而空間后處理采用超像素圖像分割方法。這種方法極為簡(jiǎn)單但卻是被首次提出,加入超像素圖像分割空間后處理,能改善高光譜圖像分類效果。
[Abstract]:Hyperspectral imagery, which originated in the 1980s, is a great leap forward in remote sensing technology. Compared with traditional visible and multispectral imagery, hyperspectral imagery can provide more abundant information of surface coverage and surface features, and has great potential in space and military fields. Therefore, it has attracted great attention of scholars at home and abroad and has become a current one. However, how to follow the "non-linear" and "non-stationary" nature of hyperspectral data and make full use of the collected image information to improve the ability of classification and recognition of ground objects has become an urgent problem in the promotion and application of hyperspectral remote sensing technology. However, there is no complete and accepted theoretical foundation so far. Therefore, how to improve the EMD theoretically, especially the "up" or "down" phenomena in the suppression of the endpoint effect and the envelopment calculation, is an important issue. Elimination is still a major challenge for researchers. This paper focuses on the theoretical improvement of EMD algorithm and its application in hyperspectral image classification. On the one hand, based on the grey model and optimization theory, EMD is improved from the aspects of end-effect suppression and envelope extraction, and the improved EMD is proposed. On the other hand, hyperspectral image classification based on sparse Representation Classifier (SRC) and super-pixel image segmentation algorithm is studied. The main research contents and innovations of this paper are as follows: 1. A Gray Mode-based EMD (GM-EMD) endpoint effect suppression method is proposed. The endpoint effect is an open theoretical problem in EMD algorithm. It is caused by the fact that the extreme points near the two ends of the signal can not be accurately determined. This paper first proves that the extreme points and envelopes are very important to one-dimensional EMD, and then it is important to the existing single-dimensional EMD in the discretization process of differential equations. The variable grey model is improved and the GM-EMD method is proposed. On the premise of not changing the original signal characteristics, the single variable grey model is fully utilized for small amount of data prediction, small amount of calculation and high precision of short-term prediction. The signal in one-dimensional EMD iteration process is extended outward by two points, and the end-point effect of one-dimensional EMD is effectively suppressed. One-dimensional EMD envelope extraction method based on Alternating Direction Method of Multipliers (ADMM) is proposed. Since the signal at the position of non-extreme points is not constrained in the spline interpolation process, it is easy to cause "up" or "down" phenomena. Compared with spline interpolation, it can effectively eliminate the "up" or "down" phenomena and get more accurate decomposition results. A two-dimensional EMD (Gray Mode-based Bi-dimensional EMD, GM-BEMD) endpoint effect suppression algorithm based on multivariable grey model is studied. The problem of end effect in two-dimensional EMD (Bi-dimensional EMD, BEMD) is caused. Therefore, a GM-BEMD method is proposed, which extends the image to its surroundings by a multivariate grey model based on the complex Simpson formula, and then decomposes the extended image with the traditional BEMD method to obtain the extended two-dimensional intrinsic modal function (Bi-dimensional Intrins). IC Mode Function (BIMF) and Residual, and then intercept the decomposition results corresponding to the original image region to suppress the BEMD endpoint effect. The spectral-spatial feature classification method based on Kernel-based Sparse Multitask Learning Classi-fier (KSMTLC) is studied. Hyperspectral spectral spectral-spatial features are solved by Accelerated Proximal Gradient (APG). Compared with single spectral or spatial features, KSMTLC has better classification performance. Spectral-spatial feature classification based on support vector machine (SVM) and superpixel image segmentation is studied. The initial classification result of hyperspectral feature is obtained by spectral feature, and then the initial classification result is modified by spatial feature through post-processing. The final classification result of spectral-spatial feature is obtained by SVM, and the superpixel image segmentation is used in spatial post-processing. This method is very simple, but it is the first time proposed that the hyperspectral image classification effect can be improved by adding super-pixel image segmentation space post-processing.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP751
，
本文編號(hào)：2221632
[Abstract]:Hyperspectral imagery, which originated in the 1980s, is a great leap forward in remote sensing technology. Compared with traditional visible and multispectral imagery, hyperspectral imagery can provide more abundant information of surface coverage and surface features, and has great potential in space and military fields. Therefore, it has attracted great attention of scholars at home and abroad and has become a current one. However, how to follow the "non-linear" and "non-stationary" nature of hyperspectral data and make full use of the collected image information to improve the ability of classification and recognition of ground objects has become an urgent problem in the promotion and application of hyperspectral remote sensing technology. However, there is no complete and accepted theoretical foundation so far. Therefore, how to improve the EMD theoretically, especially the "up" or "down" phenomena in the suppression of the endpoint effect and the envelopment calculation, is an important issue. Elimination is still a major challenge for researchers. This paper focuses on the theoretical improvement of EMD algorithm and its application in hyperspectral image classification. On the one hand, based on the grey model and optimization theory, EMD is improved from the aspects of end-effect suppression and envelope extraction, and the improved EMD is proposed. On the other hand, hyperspectral image classification based on sparse Representation Classifier (SRC) and super-pixel image segmentation algorithm is studied. The main research contents and innovations of this paper are as follows: 1. A Gray Mode-based EMD (GM-EMD) endpoint effect suppression method is proposed. The endpoint effect is an open theoretical problem in EMD algorithm. It is caused by the fact that the extreme points near the two ends of the signal can not be accurately determined. This paper first proves that the extreme points and envelopes are very important to one-dimensional EMD, and then it is important to the existing single-dimensional EMD in the discretization process of differential equations. The variable grey model is improved and the GM-EMD method is proposed. On the premise of not changing the original signal characteristics, the single variable grey model is fully utilized for small amount of data prediction, small amount of calculation and high precision of short-term prediction. The signal in one-dimensional EMD iteration process is extended outward by two points, and the end-point effect of one-dimensional EMD is effectively suppressed. One-dimensional EMD envelope extraction method based on Alternating Direction Method of Multipliers (ADMM) is proposed. Since the signal at the position of non-extreme points is not constrained in the spline interpolation process, it is easy to cause "up" or "down" phenomena. Compared with spline interpolation, it can effectively eliminate the "up" or "down" phenomena and get more accurate decomposition results. A two-dimensional EMD (Gray Mode-based Bi-dimensional EMD, GM-BEMD) endpoint effect suppression algorithm based on multivariable grey model is studied. The problem of end effect in two-dimensional EMD (Bi-dimensional EMD, BEMD) is caused. Therefore, a GM-BEMD method is proposed, which extends the image to its surroundings by a multivariate grey model based on the complex Simpson formula, and then decomposes the extended image with the traditional BEMD method to obtain the extended two-dimensional intrinsic modal function (Bi-dimensional Intrins). IC Mode Function (BIMF) and Residual, and then intercept the decomposition results corresponding to the original image region to suppress the BEMD endpoint effect. The spectral-spatial feature classification method based on Kernel-based Sparse Multitask Learning Classi-fier (KSMTLC) is studied. Hyperspectral spectral spectral-spatial features are solved by Accelerated Proximal Gradient (APG). Compared with single spectral or spatial features, KSMTLC has better classification performance. Spectral-spatial feature classification based on support vector machine (SVM) and superpixel image segmentation is studied. The initial classification result of hyperspectral feature is obtained by spectral feature, and then the initial classification result is modified by spatial feature through post-processing. The final classification result of spectral-spatial feature is obtained by SVM, and the superpixel image segmentation is used in spatial post-processing. This method is very simple, but it is the first time proposed that the hyperspectral image classification effect can be improved by adding super-pixel image segmentation space post-processing.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP751
，
本文編號(hào)：2221632
本文鏈接：http://sikaile.net/guanlilunwen/gongchengguanli/2221632.html
最近更新
教材專著
