結(jié)合多特征描述和SVM的遙感影像分類研究
發(fā)布時(shí)間：2018-08-30 19:28
【摘要】：遙感影像是水利信息中的重要信息源,從遙感影像中提取所需信息是利用遙感影像的關(guān)鍵步驟。隨著遙感數(shù)據(jù)獲取手段的增多,遙感影像數(shù)據(jù)量飛速增長,如何高質(zhì)、高效地進(jìn)行遙感影像的分類顯得至關(guān)重要。本文主要探討遙感影像的自動(dòng)分類問題,在對國內(nèi)外相關(guān)文獻(xiàn)進(jìn)行閱讀、歸納的基礎(chǔ)上,做了以下研究。分析了目前該類研究中存在的考慮因素單一、研究方法綜合性不足等問題。提出了遙感影像分類研究應(yīng)結(jié)合智能算法和多特征描述來展開的觀點(diǎn)。同時(shí),根據(jù)支持向量機(jī)(SVM)在遙感影像分類領(lǐng)域的研究現(xiàn)狀,提出了將多種方法描述的紋理特征和影像的光譜特征相結(jié)合,并利用SVM分類器進(jìn)行分類的方法。介紹了SVM的基本理論、基本算法,詳細(xì)討論了SVM參數(shù)選擇算法。根據(jù)SVM的泛化誤差界,分析了SVM的小樣本特性及其對模型復(fù)雜程度的控制能力。同時(shí)對極大似然估計(jì)、最近距離(NN)、K近鄰(K-NN)、樸素貝葉斯等分類算法,就精度、效率、適用條件做了分析對比。在對灰度直方圖、Gabor小波、離散傅里葉環(huán)狀采樣和離散小波分解四種紋理描述方法進(jìn)行介紹和比較的基礎(chǔ)上,根據(jù)Gabor小波濾波器的導(dǎo)出過程,提出了尺度參數(shù)選擇的基本指導(dǎo)原則,對離散傅里葉環(huán)狀采樣方法進(jìn)行了改進(jìn),進(jìn)一步提出了DFT平均環(huán)狀采樣直方圖方法。結(jié)合多特征描述以及SVM遙感影像分類算法,基于Lib SVM、Open CV、Free Image、SQLite、QT等開源工具和C++語言開發(fā)了一套實(shí)驗(yàn)系統(tǒng),并以鄭州市西北方向某一區(qū)域的Landsat8 OLI影像為例進(jìn)行了一系列實(shí)驗(yàn)。實(shí)驗(yàn)表明,本研究所提出的SVM分類算法,其分類精度遠(yuǎn)高于最大似然估計(jì)、K近鄰、樸素貝葉斯等分類算法的精度;所選用的四種紋理描述算法均具有一定區(qū)分能力,其中Gabor小波和DFT平均環(huán)狀采樣直方圖方法區(qū)分能力最強(qiáng);結(jié)合紋理特征和光譜特征進(jìn)行SVM影像分類,可以將分類精度提高10%,總體分類精度最高可達(dá)96.2%;結(jié)合多種紋理描述算法可進(jìn)一步提高SVM的影像分類精度。實(shí)驗(yàn)中還發(fā)現(xiàn),若將區(qū)分度高的紋理描述算法和區(qū)分度低的紋理描述算法進(jìn)行組合,其分類精度反而高于多種區(qū)分度均較高的紋理描述算法的組合,本文從模型復(fù)雜度控制的角度對這一現(xiàn)象進(jìn)行了分析和解釋。
[Abstract]:Remote sensing image is an important information source in water conservancy information, and extracting the information needed from remote sensing image is a key step to use remote sensing image. With the increase of remote sensing data acquisition means, the data volume of remote sensing image is increasing rapidly. How to classify remote sensing image with high quality and efficiency is very important. This paper mainly discusses the automatic classification of remote sensing images. On the basis of reading and summing up the relevant literature at home and abroad, the following research is done. This paper analyzes the problems of single factor and lack of comprehensive research methods in this kind of research at present. The viewpoint that the classification of remote sensing images should be developed with intelligent algorithm and multi-feature description is put forward. At the same time, according to the research status of support vector machine (SVM) in remote sensing image classification, this paper proposes a method which combines the texture features described by many methods with the spectral features of the image, and uses SVM classifier to classify the image. This paper introduces the basic theory and algorithm of SVM, and discusses the SVM parameter selection algorithm in detail. According to the generalization error bound of SVM, the small sample characteristics of SVM and its ability to control the complexity of the model are analyzed. At the same time, the maximum likelihood estimation, nearest distance (NN) KNN (K-NN) and naive Bayes classification algorithms are analyzed and compared in terms of accuracy, efficiency and applicable conditions. On the basis of introducing and comparing four texture description methods, such as gray histogram Gabor wavelet, discrete Fourier ring sampling and discrete wavelet decomposition, according to the derivation process of Gabor wavelet filter, The basic guiding principle of scale parameter selection is put forward, the discrete Fourier ring sampling method is improved, and the DFT average annular sampling histogram method is further proposed. Combined with multi-feature description and SVM remote sensing image classification algorithm, an experimental system is developed based on open source tools such as Lib SVM,Open CV,Free Image,SQLite,QT and C language, and a series of experiments are carried out with the example of Landsat8 OLI image in a certain area northwest of Zhengzhou. Experimental results show that the classification accuracy of the proposed SVM classification algorithm is much higher than that of the maximum likelihood estimation (MLE) algorithm and the naive Bayes classification algorithm. Among them, Gabor wavelet and DFT mean ring sampling histogram have the strongest ability to distinguish, and combine texture feature and spectral feature to classify SVM image. The classification accuracy can be improved by 10%, and the overall classification accuracy can be up to 96.2.The SVM image classification accuracy can be further improved by combining various texture description algorithms. It is also found in the experiment that if the combination of texture description algorithm with high classification degree and texture description algorithm with low differentiation degree is combined, the classification accuracy of the algorithm is higher than that of many texture description algorithms with high degree of differentiation. This paper analyzes and explains this phenomenon from the angle of model complexity control.
【學(xué)位授予單位】：鄭州大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TP751
本文編號(hào)：2214063
[Abstract]:Remote sensing image is an important information source in water conservancy information, and extracting the information needed from remote sensing image is a key step to use remote sensing image. With the increase of remote sensing data acquisition means, the data volume of remote sensing image is increasing rapidly. How to classify remote sensing image with high quality and efficiency is very important. This paper mainly discusses the automatic classification of remote sensing images. On the basis of reading and summing up the relevant literature at home and abroad, the following research is done. This paper analyzes the problems of single factor and lack of comprehensive research methods in this kind of research at present. The viewpoint that the classification of remote sensing images should be developed with intelligent algorithm and multi-feature description is put forward. At the same time, according to the research status of support vector machine (SVM) in remote sensing image classification, this paper proposes a method which combines the texture features described by many methods with the spectral features of the image, and uses SVM classifier to classify the image. This paper introduces the basic theory and algorithm of SVM, and discusses the SVM parameter selection algorithm in detail. According to the generalization error bound of SVM, the small sample characteristics of SVM and its ability to control the complexity of the model are analyzed. At the same time, the maximum likelihood estimation, nearest distance (NN) KNN (K-NN) and naive Bayes classification algorithms are analyzed and compared in terms of accuracy, efficiency and applicable conditions. On the basis of introducing and comparing four texture description methods, such as gray histogram Gabor wavelet, discrete Fourier ring sampling and discrete wavelet decomposition, according to the derivation process of Gabor wavelet filter, The basic guiding principle of scale parameter selection is put forward, the discrete Fourier ring sampling method is improved, and the DFT average annular sampling histogram method is further proposed. Combined with multi-feature description and SVM remote sensing image classification algorithm, an experimental system is developed based on open source tools such as Lib SVM,Open CV,Free Image,SQLite,QT and C language, and a series of experiments are carried out with the example of Landsat8 OLI image in a certain area northwest of Zhengzhou. Experimental results show that the classification accuracy of the proposed SVM classification algorithm is much higher than that of the maximum likelihood estimation (MLE) algorithm and the naive Bayes classification algorithm. Among them, Gabor wavelet and DFT mean ring sampling histogram have the strongest ability to distinguish, and combine texture feature and spectral feature to classify SVM image. The classification accuracy can be improved by 10%, and the overall classification accuracy can be up to 96.2.The SVM image classification accuracy can be further improved by combining various texture description algorithms. It is also found in the experiment that if the combination of texture description algorithm with high classification degree and texture description algorithm with low differentiation degree is combined, the classification accuracy of the algorithm is higher than that of many texture description algorithms with high degree of differentiation. This paper analyzes and explains this phenomenon from the angle of model complexity control.
【學(xué)位授予單位】：鄭州大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TP751
【參考文獻(xiàn)】
相關(guān)期刊論文 前7條
1 明冬萍;駱劍承;沈占鋒;;基于GMRF-SVM的高分辨率遙感影像目標(biāo)區(qū)域劃分方法[J];測繪科學(xué);2009年02期
2 王立志;黃鴻;馮海亮;;基于SSMFA與kNNS算法的高光譜遙感影像分類[J];電子學(xué)報(bào);2012年04期
3 唐銀鳳;黃志明;黃榮娟;姜佳欣;盧昕;;基于多特征提取和SVM分類器的紋理圖像分類[J];計(jì)算機(jī)應(yīng)用與軟件;2011年06期
4 金龍,況雪源,黃海洪,覃志年,王業(yè)宏;人工神經(jīng)網(wǎng)絡(luò)預(yù)報(bào)模型的過擬合研究[J];氣象學(xué)報(bào);2004年01期
5 韓思奇,王蕾;圖像分割的閾值法綜述[J];系統(tǒng)工程與電子技術(shù);2002年06期
6 劉龍飛,陳云浩,李京;遙感影像紋理分析方法綜述與展望[J];遙感技術(shù)與應(yīng)用;2003年06期
7 駱劍承,周成虎,梁怡,馬江洪;支撐向量機(jī)及其遙感影像空間特征提取和分類的應(yīng)用研究[J];遙感學(xué)報(bào);2002年01期
，本文編號(hào)：2214063
本文鏈接：http://sikaile.net/guanlilunwen/gongchengguanli/2214063.html
最近更新
教材專著
