基于紋理分析的高分辨率影像面向?qū)ο蠓诸愌芯?/H1>
發(fā)布時間：2018-04-19 23:31
本文選題：面向?qū)ο蠓诸?/strong> + 灰度共生矩陣 ； 參考：《北京師范大學(xué)》2014年碩士論文
【摘要】：隨著衛(wèi)星遙感數(shù)據(jù)空間分辨率的不斷提高，使用傳統(tǒng)的基于像元的遙感影像處理方法不僅無法充分利用高分辨率影像中的空間細節(jié)信息，還會因為“同物異譜”以及“同譜異物”的現(xiàn)象導(dǎo)致分類結(jié)果出現(xiàn)較多的漏分和誤分，同時分類結(jié)果還會呈現(xiàn)嚴重的“椒鹽噪聲”，嚴重影響了分類精度。應(yīng)運而生的面向?qū)ο蠓诸惙椒�，能有效的抑制上述問題，因此受到了眾多學(xué)者的關(guān)注。 紋理信息作為一種重要的影像空間特征信息，在遙感影像分類中有著廣泛的應(yīng)用。眾多學(xué)者利用紋理信息輔助分類獲得了較好的效果。但是目前的研究大多基于傳統(tǒng)的面向像元分類，即便是基于面向?qū)ο蠓诸惖募y理研究也多采用了單一尺度的面向?qū)ο蠓诸�。并未就紋理信息在多尺度面向?qū)ο蠓诸愔袑Ψ诸惥鹊挠绊戇M行深入研究。因此本文針對前人研究，使用唐山市豐南區(qū)的IKONOS數(shù)據(jù)構(gòu)建了多尺度的面向?qū)ο蠓诸愺w系，并以此研究了紋理信息的添加對于分類精度的影響，得到以下的研究成果： 本文通過ESP(Estimation of Scale Parameters)工具和多次試驗，確定了研究區(qū)域內(nèi)主要地類最適宜的分割尺度和分割參數(shù)，建立了三級的多尺度分割層次（81,47,16），并依此建立了多級的分類體系，體現(xiàn)了多尺度分割在面向?qū)ο蠓诸愔械膬?yōu)勢。 在面向?qū)ο蠓诸惖幕A(chǔ)上，提取了8種GLCM（灰度共生矩陣）紋理和3種LSS（局部空間統(tǒng)計）紋理，在SVM（Support Vector Machine）和NN（最鄰近）兩種分類器下，研究了不同紋理對于總體精度以及各類別PA（用戶精度）和UA（制圖精度）的影響。實驗證明，該實驗條件下添加單紋理信息能有效提高總體精度以及大部分類別的PA和UA，在SVM分類器下，紋理信息的添加對總體精度的影響較小，均在1%左右，而在NN分類器下，紋理信息的添加對總體精度的影響較大，Geary's C紋理擁有最佳的總體精度（79.06%），相比單純使用多光譜的分類結(jié)果提升了4.6%的總體精度。選擇了部分紋理來研究紋理尺度參數(shù)對于分類精度的影響，結(jié)果顯示尺度參數(shù)的變化會對分類結(jié)果產(chǎn)生一定的影響，，但這種影響會因為面向?qū)ο蠓诸惐旧淼臋C制問題而削弱。 提出了一種基于蟻群算法的最優(yōu)紋理特征組合選擇方法，能夠在保證較高分類精度的情況下大幅縮減特征維數(shù)，可以在未分類的情況下，僅根據(jù)樣本就可以得到最優(yōu)的特征組合。得到了兩種分類器在實驗區(qū)內(nèi)的最優(yōu)紋理特征組合，并進行了驗證。
[Abstract]:With the continuous improvement of spatial resolution of satellite remote sensing data, the traditional pixel based remote sensing image processing method can not make full use of the spatial details of high-resolution images. Because of the phenomenon of "isomorphism" and "isospectral foreign body", there will be more missing points and false scores in the classification results. At the same time, the classification results will also present serious "salt and pepper noise", which seriously affects the classification accuracy. The object-oriented classification method which arises at the historic moment can restrain the above problems effectively, so many scholars pay close attention to it. As an important spatial feature information, texture information is widely used in remote sensing image classification. Many scholars use texture information to assist classification to obtain better results. However, most of the current researches are based on traditional pixel oriented classification, and even the texture research based on object oriented classification is mostly based on single scale object oriented classification. The effect of texture information on classification accuracy in multi-scale object-oriented classification is not studied. Therefore, this paper constructs a multi-scale object-oriented classification system based on the IKONOS data of Fengnan District, Tangshan City, and studies the effect of texture information on classification accuracy. The following research results are obtained: By means of ESP(Estimation of Scale parameters tool and many experiments, this paper determines the most suitable segmentation scale and segmentation parameters for the main ground classes in the study area, and establishes a multi-scale multi-scale segmentation level of 81D 4716m, based on which a multilevel classification system is established. It shows the advantage of multi-scale segmentation in object-oriented classification. On the basis of object oriented classification, eight GLCM textures and three LSS (Local Spatial Statistics) textures are extracted, which are based on SVM(Support Vector Machine and NN (nearest neighbor) classifiers. The effects of different textures on the overall accuracy, as well as various types of PAs (user accuracy) and UA( cartographic accuracy) are studied. Experiments show that adding single texture information can effectively improve the overall precision and the PA and UAA of most categories under the experimental condition. In SVM classifier, the effect of adding texture information on the overall accuracy is less, which is about 1%, while in NN classifier, the effect of adding texture information on the overall accuracy is about 1%. The addition of texture information has a great influence on the overall precision. The GearyCtexture has the best overall precision 79.060.Compared with the classification results using multi-spectral method, the overall accuracy is increased by 4.6%. Some textures are selected to study the effect of texture scale parameters on classification accuracy. The result shows that the variation of scale parameters will have a certain impact on the classification results, but this effect will be weakened by the mechanism of object oriented classification. An optimal texture feature combination selection method based on ant colony algorithm is proposed, which can greatly reduce the feature dimension in the case of high classification accuracy, and can be used in the case of no classification. The optimal feature combination can be obtained only according to the sample. The optimal texture feature combinations of the two classifiers in the experimental region are obtained and verified.
【學(xué)位授予單位】：北京師范大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：P237
【參考文獻】
相關(guān)期刊論文 前10條
1 陳晨;張友靜;;基于多尺度紋理和光譜信息的SVM分類研究[J];測繪科學(xué);2009年01期
2 宋剛賢;潘劍君;朱文娟;;IKONOS影像的最佳融合技術(shù)研究[J];測繪科學(xué);2009年02期
3 劉小平,彭曉鵑,艾彬;像元信息分解和決策樹相結(jié)合的影像分類方法[J];地理與地理信息科學(xué);2004年06期
4 胡玉福;鄧良基;匡先輝;王鵬;何莎;熊玲;;基于紋理特征的高分辨率遙感圖像土地利用分類研究[J];地理與地理信息科學(xué);2011年05期
5 鄧媛媛;巫兆聰;易俐娜;胡忠文;龔正娟;;面向?qū)ο蟮母叻直媛视跋褶r(nóng)用地分類[J];國土資源遙感;2010年04期
6 競霞;邵美云;;基于地表覆蓋分類的IKONOS影像融合算法分析與評價[J];安徽農(nóng)業(yè)科學(xué);2012年27期
7 葉志偉;鄭肇葆;萬幼川;虞欣;;基于蟻群優(yōu)化的特征選擇新方法[J];武漢大學(xué)學(xué)報(信息科學(xué)版);2007年12期
8 傅文杰;林明森;;利用SVM與灰度共生矩陣從QuickBird影像中提取枇杷信息[J];遙感技術(shù)與應(yīng)用;2010年05期
9 胡榮明;魏曼;楊成斌;賀俊斌;;以SPOT5遙感數(shù)據(jù)為例比較基于像素與面向?qū)ο蟮姆诸惙椒╗J];遙感技術(shù)與應(yīng)用;2012年03期
10 張錦水;何春陽;潘耀忠;李京;;基于SVM的多源信息復(fù)合的高空間分辨率遙感數(shù)據(jù)分類研究[J];遙感學(xué)報;2006年01期
本文編號：1775242
本文鏈接：http://sikaile.net/kejilunwen/dizhicehuilunwen/1775242.html
本文選題：面向?qū)ο蠓诸?/strong> + 灰度共生矩陣 ； 參考：《北京師范大學(xué)》2014年碩士論文
【摘要】：隨著衛(wèi)星遙感數(shù)據(jù)空間分辨率的不斷提高，使用傳統(tǒng)的基于像元的遙感影像處理方法不僅無法充分利用高分辨率影像中的空間細節(jié)信息，還會因為“同物異譜”以及“同譜異物”的現(xiàn)象導(dǎo)致分類結(jié)果出現(xiàn)較多的漏分和誤分，同時分類結(jié)果還會呈現(xiàn)嚴重的“椒鹽噪聲”，嚴重影響了分類精度。應(yīng)運而生的面向?qū)ο蠓诸惙椒�，能有效的抑制上述問題，因此受到了眾多學(xué)者的關(guān)注。 紋理信息作為一種重要的影像空間特征信息，在遙感影像分類中有著廣泛的應(yīng)用。眾多學(xué)者利用紋理信息輔助分類獲得了較好的效果。但是目前的研究大多基于傳統(tǒng)的面向像元分類，即便是基于面向?qū)ο蠓诸惖募y理研究也多采用了單一尺度的面向?qū)ο蠓诸�。并未就紋理信息在多尺度面向?qū)ο蠓诸愔袑Ψ诸惥鹊挠绊戇M行深入研究。因此本文針對前人研究，使用唐山市豐南區(qū)的IKONOS數(shù)據(jù)構(gòu)建了多尺度的面向?qū)ο蠓诸愺w系，并以此研究了紋理信息的添加對于分類精度的影響，得到以下的研究成果： 本文通過ESP(Estimation of Scale Parameters)工具和多次試驗，確定了研究區(qū)域內(nèi)主要地類最適宜的分割尺度和分割參數(shù)，建立了三級的多尺度分割層次（81,47,16），并依此建立了多級的分類體系，體現(xiàn)了多尺度分割在面向?qū)ο蠓诸愔械膬?yōu)勢。 在面向?qū)ο蠓诸惖幕A(chǔ)上，提取了8種GLCM（灰度共生矩陣）紋理和3種LSS（局部空間統(tǒng)計）紋理，在SVM（Support Vector Machine）和NN（最鄰近）兩種分類器下，研究了不同紋理對于總體精度以及各類別PA（用戶精度）和UA（制圖精度）的影響。實驗證明，該實驗條件下添加單紋理信息能有效提高總體精度以及大部分類別的PA和UA，在SVM分類器下，紋理信息的添加對總體精度的影響較小，均在1%左右，而在NN分類器下，紋理信息的添加對總體精度的影響較大，Geary's C紋理擁有最佳的總體精度（79.06%），相比單純使用多光譜的分類結(jié)果提升了4.6%的總體精度。選擇了部分紋理來研究紋理尺度參數(shù)對于分類精度的影響，結(jié)果顯示尺度參數(shù)的變化會對分類結(jié)果產(chǎn)生一定的影響，，但這種影響會因為面向?qū)ο蠓诸惐旧淼臋C制問題而削弱。 提出了一種基于蟻群算法的最優(yōu)紋理特征組合選擇方法，能夠在保證較高分類精度的情況下大幅縮減特征維數(shù)，可以在未分類的情況下，僅根據(jù)樣本就可以得到最優(yōu)的特征組合。得到了兩種分類器在實驗區(qū)內(nèi)的最優(yōu)紋理特征組合，并進行了驗證。
[Abstract]:With the continuous improvement of spatial resolution of satellite remote sensing data, the traditional pixel based remote sensing image processing method can not make full use of the spatial details of high-resolution images. Because of the phenomenon of "isomorphism" and "isospectral foreign body", there will be more missing points and false scores in the classification results. At the same time, the classification results will also present serious "salt and pepper noise", which seriously affects the classification accuracy. The object-oriented classification method which arises at the historic moment can restrain the above problems effectively, so many scholars pay close attention to it. As an important spatial feature information, texture information is widely used in remote sensing image classification. Many scholars use texture information to assist classification to obtain better results. However, most of the current researches are based on traditional pixel oriented classification, and even the texture research based on object oriented classification is mostly based on single scale object oriented classification. The effect of texture information on classification accuracy in multi-scale object-oriented classification is not studied. Therefore, this paper constructs a multi-scale object-oriented classification system based on the IKONOS data of Fengnan District, Tangshan City, and studies the effect of texture information on classification accuracy. The following research results are obtained: By means of ESP(Estimation of Scale parameters tool and many experiments, this paper determines the most suitable segmentation scale and segmentation parameters for the main ground classes in the study area, and establishes a multi-scale multi-scale segmentation level of 81D 4716m, based on which a multilevel classification system is established. It shows the advantage of multi-scale segmentation in object-oriented classification. On the basis of object oriented classification, eight GLCM textures and three LSS (Local Spatial Statistics) textures are extracted, which are based on SVM(Support Vector Machine and NN (nearest neighbor) classifiers. The effects of different textures on the overall accuracy, as well as various types of PAs (user accuracy) and UA( cartographic accuracy) are studied. Experiments show that adding single texture information can effectively improve the overall precision and the PA and UAA of most categories under the experimental condition. In SVM classifier, the effect of adding texture information on the overall accuracy is less, which is about 1%, while in NN classifier, the effect of adding texture information on the overall accuracy is about 1%. The addition of texture information has a great influence on the overall precision. The GearyCtexture has the best overall precision 79.060.Compared with the classification results using multi-spectral method, the overall accuracy is increased by 4.6%. Some textures are selected to study the effect of texture scale parameters on classification accuracy. The result shows that the variation of scale parameters will have a certain impact on the classification results, but this effect will be weakened by the mechanism of object oriented classification. An optimal texture feature combination selection method based on ant colony algorithm is proposed, which can greatly reduce the feature dimension in the case of high classification accuracy, and can be used in the case of no classification. The optimal feature combination can be obtained only according to the sample. The optimal texture feature combinations of the two classifiers in the experimental region are obtained and verified.
【學(xué)位授予單位】：北京師范大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：P237
【參考文獻】
相關(guān)期刊論文 前10條
1 陳晨;張友靜;;基于多尺度紋理和光譜信息的SVM分類研究[J];測繪科學(xué);2009年01期
2 宋剛賢;潘劍君;朱文娟;;IKONOS影像的最佳融合技術(shù)研究[J];測繪科學(xué);2009年02期
3 劉小平,彭曉鵑,艾彬;像元信息分解和決策樹相結(jié)合的影像分類方法[J];地理與地理信息科學(xué);2004年06期
4 胡玉福;鄧良基;匡先輝;王鵬;何莎;熊玲;;基于紋理特征的高分辨率遙感圖像土地利用分類研究[J];地理與地理信息科學(xué);2011年05期
5 鄧媛媛;巫兆聰;易俐娜;胡忠文;龔正娟;;面向?qū)ο蟮母叻直媛视跋褶r(nóng)用地分類[J];國土資源遙感;2010年04期
6 競霞;邵美云;;基于地表覆蓋分類的IKONOS影像融合算法分析與評價[J];安徽農(nóng)業(yè)科學(xué);2012年27期
7 葉志偉;鄭肇葆;萬幼川;虞欣;;基于蟻群優(yōu)化的特征選擇新方法[J];武漢大學(xué)學(xué)報(信息科學(xué)版);2007年12期
8 傅文杰;林明森;;利用SVM與灰度共生矩陣從QuickBird影像中提取枇杷信息[J];遙感技術(shù)與應(yīng)用;2010年05期
9 胡榮明;魏曼;楊成斌;賀俊斌;;以SPOT5遙感數(shù)據(jù)為例比較基于像素與面向?qū)ο蟮姆诸惙椒╗J];遙感技術(shù)與應(yīng)用;2012年03期
10 張錦水;何春陽;潘耀忠;李京;;基于SVM的多源信息復(fù)合的高空間分辨率遙感數(shù)據(jù)分類研究[J];遙感學(xué)報;2006年01期
本文編號：1775242
本文鏈接：http://sikaile.net/kejilunwen/dizhicehuilunwen/1775242.html
最近更新
教材專著
