基于核空譜信息挖掘的高光譜圖像分類方法研究
發(fā)布時(shí)間：2018-07-23 09:16
【摘要】：遙感技術(shù)發(fā)展的總趨勢(shì)是以更高空間分辨率、更高光譜分辨率、更高時(shí)間分辨率對(duì)地球進(jìn)行探測(cè)，進(jìn)而提供地表覆蓋環(huán)境更加精確、細(xì)致的觀測(cè)信息。自上世紀(jì)80年代光譜成像技術(shù)被提出以來(lái)，高光譜成像已經(jīng)成為一種重要的遙感探測(cè)手段，其本質(zhì)在于能夠同時(shí)提供地物分布的空間信息和較高分辨率的光譜信息。因此，高光譜遙感圖像數(shù)據(jù)處理與信息挖掘技術(shù)研究具有重要的理論意義和巨大的應(yīng)用價(jià)值，已成為遙感成像探測(cè)與信息處理領(lǐng)域的研究熱點(diǎn)。 本論文以高光譜遙感圖像地物分類為背景，以核學(xué)習(xí)理論和方法為技術(shù)框架，針對(duì)高光譜遙感圖像的特征提取、光譜分類和空間-光譜信息聯(lián)合分類等問(wèn)題開展研究，重點(diǎn)研究了基于單核/多核學(xué)習(xí)理論的高光譜圖像光譜信息和空譜聯(lián)合信息挖掘技術(shù)，旨在充分利用高光譜圖像所提供的空間-光譜聯(lián)合信息，提高地物分類性能。本論文研究的主要工作體現(xiàn)在： 首先，整體研究核學(xué)習(xí)理論及其最新進(jìn)展——多核學(xué)習(xí)理論及方法，奠定本論文研究?jī)?nèi)容的理論基礎(chǔ)。論文在概要介紹了核學(xué)習(xí)理論及核方法設(shè)計(jì)的基礎(chǔ)上，研究和分析了多核學(xué)習(xí)理論所涉及到的多核構(gòu)造、優(yōu)化學(xué)習(xí)方法，在理論上對(duì)合成核和多尺度核方法進(jìn)行了研究。 其次，立足于高光譜圖像數(shù)據(jù)自身統(tǒng)計(jì)特性，將數(shù)據(jù)特性同核方法設(shè)計(jì)有機(jī)結(jié)合，提出了基于子空間調(diào)制核的高光譜圖像特征提取方法。論文依據(jù)成像光譜探測(cè)原理所決定的高光譜圖像數(shù)據(jù)子空間特性，研究了三種子空間劃分的度量準(zhǔn)則；在此基礎(chǔ)上，設(shè)計(jì)了子空間調(diào)制核函數(shù)，以使源自成像機(jī)理的數(shù)據(jù)子空間特性融入到核設(shè)計(jì)及特征提取方法中，進(jìn)而達(dá)到充分利用高光譜成像和數(shù)據(jù)特性的目的；論文利用地物分類實(shí)驗(yàn)驗(yàn)證了所提出的子空間調(diào)制核方法的有效性，即在提取特征的同時(shí)有效地提高分類性能。 再次，以基于光譜信息的地物分類應(yīng)用為直接導(dǎo)引，重點(diǎn)研究了多尺度多核學(xué)習(xí)分類模型，提出了多尺度多核最優(yōu)集成學(xué)習(xí)方法。針對(duì)以支持向量機(jī)為代表的傳統(tǒng)核方法學(xué)習(xí)能力受限于單核函數(shù)的問(wèn)題，本文提出了多尺度多核學(xué)習(xí)模型；進(jìn)一步，將多尺度多核學(xué)習(xí)問(wèn)題分解為多尺度核無(wú)監(jiān)督學(xué)習(xí)和支持向量機(jī)優(yōu)化兩個(gè)子問(wèn)題，并提出了秩“1”約束下的基于非負(fù)矩陣分解和核非負(fù)矩陣分解的多核最優(yōu)集成學(xué)習(xí)方法。相比于傳統(tǒng)支持向量機(jī)和當(dāng)前主流的多核學(xué)習(xí)方法，本文所提出的方法具有更優(yōu)的性能。 最后，為充分挖掘和利用高光譜圖像的空-譜信息，構(gòu)建了多特征多核學(xué)習(xí)模型，將空間特征和光譜特征有機(jī)地融合在多核學(xué)習(xí)理論框架下，進(jìn)一步提升了高光譜圖像地物分類能力。論文構(gòu)建了多特征多核學(xué)習(xí)模型，提出了多特征多核最優(yōu)集成學(xué)習(xí)方法，用以實(shí)現(xiàn)空譜特征的聯(lián)合分類，論文針對(duì)高光譜圖像自身提取的空間-光譜信息聯(lián)合、高分辨率可見(jiàn)光圖像空間信息和高光譜圖像光譜信息聯(lián)合兩種情況進(jìn)行了研究。首先，，針對(duì)三類典型的高光譜圖像空間特征(局部區(qū)域矩特征、Gabor空間紋理特征、多尺度形態(tài)學(xué)特征)進(jìn)行了多核分類研究，分析了不同空間特征對(duì)于不同數(shù)據(jù)源的適應(yīng)性；其次，分別從高空間分辨率的可見(jiàn)光圖像和高光譜分辨率的高光譜圖像中分別提取空間特征和光譜信息，構(gòu)建多特征聯(lián)合分類模型及方法。真實(shí)數(shù)據(jù)的實(shí)驗(yàn)結(jié)果表明，本文提出的模型及方法有效地提高了空譜特征可利用性和高光譜遙感圖像分類性能。
[Abstract]:The general trend of the development of remote sensing technology is to detect the earth with higher spatial resolution , higher spectral resolution and higher temporal resolution , thus providing more accurate and detailed observation information of the surface covering environment . Since the spectral imaging technology of the 1980s has been proposed , hyperspectral imaging has become an important sensing means of remote sensing , which is essential in providing spatial information and high resolution spectral information of the geographical distribution . Therefore , the research of hyperspectral remote sensing image data processing and information mining has important theoretical significance and great application value , and has become a hot spot in the field of remote sensing imaging detection and information processing .
Based on the classification of hyperspectral remote sensing images as background , the paper studies the feature extraction , spectral classification and spatial - spectral information joint classification of hyperspectral remote sensing images by using kernel learning theory and method , and focuses on the high spectral image spectral information and space - spectrum joint information mining technology based on single - core / multi - core learning theory , aiming at fully utilizing the spatial - spectrum joint information provided by hyperspectral images and improving the classification performance of the terrain .
First , the whole study of the theory of nuclear learning and the latest development of multi - core learning theory and method lays a theoretical foundation for the research content of this paper . Based on the summary of the theory of nuclear learning and the design of nuclear method , this paper studies and analyzes the multi - core structure and optimization learning method involved in the multi - core learning theory , and studies the synthetic kernel and multi - scale nuclear method in theory .
Secondly , based on the statistical characteristics of hyperspectral image data , a method for extracting hyperspectral image features based on subspace modulation kernel is proposed . Based on the characteristics of hyperspectral image data subspace determined by imaging spectrum detection principle , the paper studies the measurement criterion of three - seed spatial division .
On this basis , the subspace modulation kernel function is designed so that the data subspace characteristics derived from the imaging mechanism are integrated into the kernel design and feature extraction method , so that the purpose of fully utilizing hyperspectral imaging and data characteristics is achieved ;
In this paper , the validity of the proposed subspace modulation kernel method is verified by means of classification experiments , that is , the classification performance can be improved effectively while extracting features .
Thirdly , the multi - scale multi - core learning classification model is focused on multi - scale multi - core learning classification model based on spectral information , and multi - scale multi - core optimal integrated learning method is proposed .
Further , the multi - scale multi - core learning problem is decomposed into two sub - problems of multi - scale nuclear non - supervised learning and support vector machine optimization , and a multi - core optimal integrated learning method based on non - negative matrix factorization and kernel non - negative matrix decomposition under the constraint of rank " 1 " is proposed . Compared with the traditional support vector machine and the current mainstream multi - core learning method , the method provided by the present invention has better performance .
Finally , the multi - feature multi - core learning model is constructed for the purpose of fully excavating and utilizing the space - spectrum information of hyperspectral image . The multi - feature multi - core learning model is constructed . The multi - feature multi - core learning model is constructed , and the multi - feature multi - core optimal integrated learning method is proposed to realize the joint classification of the spatial - spectral information , the high - resolution visible image space information and the hyperspectral image spectral information .
Secondly , the spatial features and spectral information are extracted from the high spectral images with high spatial resolution and high spectral resolution respectively . The multi - feature joint classification model and method are constructed . The experimental results of real data show that the model and method proposed in this paper effectively improve the classification performance of the spatial spectral features and hyperspectral remote sensing images .
【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;O433
本文編號(hào)：2138933
[Abstract]:The general trend of the development of remote sensing technology is to detect the earth with higher spatial resolution , higher spectral resolution and higher temporal resolution , thus providing more accurate and detailed observation information of the surface covering environment . Since the spectral imaging technology of the 1980s has been proposed , hyperspectral imaging has become an important sensing means of remote sensing , which is essential in providing spatial information and high resolution spectral information of the geographical distribution . Therefore , the research of hyperspectral remote sensing image data processing and information mining has important theoretical significance and great application value , and has become a hot spot in the field of remote sensing imaging detection and information processing .
Based on the classification of hyperspectral remote sensing images as background , the paper studies the feature extraction , spectral classification and spatial - spectral information joint classification of hyperspectral remote sensing images by using kernel learning theory and method , and focuses on the high spectral image spectral information and space - spectrum joint information mining technology based on single - core / multi - core learning theory , aiming at fully utilizing the spatial - spectrum joint information provided by hyperspectral images and improving the classification performance of the terrain .
First , the whole study of the theory of nuclear learning and the latest development of multi - core learning theory and method lays a theoretical foundation for the research content of this paper . Based on the summary of the theory of nuclear learning and the design of nuclear method , this paper studies and analyzes the multi - core structure and optimization learning method involved in the multi - core learning theory , and studies the synthetic kernel and multi - scale nuclear method in theory .
Secondly , based on the statistical characteristics of hyperspectral image data , a method for extracting hyperspectral image features based on subspace modulation kernel is proposed . Based on the characteristics of hyperspectral image data subspace determined by imaging spectrum detection principle , the paper studies the measurement criterion of three - seed spatial division .
On this basis , the subspace modulation kernel function is designed so that the data subspace characteristics derived from the imaging mechanism are integrated into the kernel design and feature extraction method , so that the purpose of fully utilizing hyperspectral imaging and data characteristics is achieved ;
In this paper , the validity of the proposed subspace modulation kernel method is verified by means of classification experiments , that is , the classification performance can be improved effectively while extracting features .
Thirdly , the multi - scale multi - core learning classification model is focused on multi - scale multi - core learning classification model based on spectral information , and multi - scale multi - core optimal integrated learning method is proposed .
Further , the multi - scale multi - core learning problem is decomposed into two sub - problems of multi - scale nuclear non - supervised learning and support vector machine optimization , and a multi - core optimal integrated learning method based on non - negative matrix factorization and kernel non - negative matrix decomposition under the constraint of rank " 1 " is proposed . Compared with the traditional support vector machine and the current mainstream multi - core learning method , the method provided by the present invention has better performance .
Finally , the multi - feature multi - core learning model is constructed for the purpose of fully excavating and utilizing the space - spectrum information of hyperspectral image . The multi - feature multi - core learning model is constructed . The multi - feature multi - core learning model is constructed , and the multi - feature multi - core optimal integrated learning method is proposed to realize the joint classification of the spatial - spectral information , the high - resolution visible image space information and the hyperspectral image spectral information .
Secondly , the spatial features and spectral information are extracted from the high spectral images with high spatial resolution and high spectral resolution respectively . The multi - feature joint classification model and method are constructed . The experimental results of real data show that the model and method proposed in this paper effectively improve the classification performance of the spatial spectral features and hyperspectral remote sensing images .
【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;O433
【參考文獻(xiàn)】
相關(guān)期刊論文 前3條
1 楊國(guó)鵬;余旭初;;高光譜遙感影像的廣義判別分析特征提取[J];測(cè)繪科學(xué)技術(shù)學(xué)報(bào);2007年02期
2 汪洪橋;孫富春;蔡艷寧;陳寧;丁林閣;;多核學(xué)習(xí)方法[J];自動(dòng)化學(xué)報(bào);2010年08期
3 高恒振;萬(wàn)建偉;王力寶;徐湛;;基于譜域-空域組合核函數(shù)的高光譜圖像分類技術(shù)研究[J];信號(hào)處理;2011年05期
本文編號(hào)：2138933
本文鏈接：http://sikaile.net/guanlilunwen/gongchengguanli/2138933.html
最近更新
教材專著
