本文關鍵詞：基于WorldView-2數(shù)據(jù)的城市典型綠化樹種分類　出處：《內蒙古農業(yè)大學》2016年博士論文　論文類型：學位論文

  更多相關文章： WorldView-2 呼和浩特 綠化樹種 影像特征 遞歸特征消除 最大似然 支持向量機

【摘要】：通過遙感技術識別樹種是尚未解決的難題之一,也是廣大學者關注的焦點問題之一。目前基于高分辨率影像及輔助數(shù)據(jù)的樹種分類已經取得了一定的成果,但依然存在許多諸如側重影像信息維度窄、影像特征構建與篩選不科學、分類器休斯現(xiàn)象未解決等問題。本研究以呼和浩特市WorldView-2影像為數(shù)據(jù)源,經影像預處理,確定分類樹種,構建影像高維光譜指數(shù)集合、紋理特征集合,基于最大似然的遞歸特征消除(MLC-RFE)選擇重要變量,規(guī)避最大似然的休斯現(xiàn)象,獲取樹種分類的最優(yōu)光譜指數(shù)子集、紋理特征子集。充分結合影像光譜波段、光譜指數(shù)、紋理等特征類型,利用最大似然對組合數(shù)據(jù)進行分類,以支持向量機的分類結果作為參照,實驗結果取得了較好的分類精度。主要研究結果如下：(1)NDVI影像中藍色屋頂、綠色塑膠操場2類地物與植被具有相似的NDVI特性,為城市植被提取造成干擾,但三者在WorldView-2八個波段中的光譜曲線存在較大差異,通過波譜角分類可實現(xiàn)三者完全分離,精準獲取到城市植被部分的影像。(2)采用最大似然對針葉樹、闊葉樹與草類進行分類,利用8月份WorldView-2影像分類的總體精度為93.9871%, Kappa系數(shù)為0.9098,利用2月份QuickBird影像分類的總體精度為96.6667%, Kappa系數(shù)為0.9500,結果表明特殊時相數(shù)據(jù)源的選擇更有利于針葉樹、闊葉樹、草類的識別。(3)基于WorldView-2光譜波段的樹種分類中,最大似然對完整8波段分類的總體精度較傳統(tǒng)4波段高10.7231%, Kappa系數(shù)高0.1253；支持向量機對完整8波段分類的總體精度較傳統(tǒng)4波段高9.9183%,Kappa系數(shù)高0.1158,表明WorldView-2新增的海岸藍色、黃、紅邊、近紅外2波段在樹種分類中具有重要的作用。(4)基于27維光譜指數(shù)的樹種分類中,NDVI6、FDI2、NREB是樹種分類中最重要的3個光譜指數(shù)；NDVI6、FDI2、NREB、ARVI、NDVI5、NDVI2、GRVI、NYR、NDVI1, IPVI、NPCI、R/RE、NDVI3、NIRNDVI、SAVI、NDVI7、NIR/GREEN、TA578、TA678是樹種分類中最優(yōu)光譜指數(shù)子集的19個成員；SL57、SL67、NDVI4、SL58、RVI、EVI、OSAVI、 SL56是導致最大似然發(fā)生休斯現(xiàn)象的8個光譜指數(shù)。(5)本研究新建的5個光譜指數(shù)SL57、SL67、SL58、TA578、TA678在MLC-RFE變量選擇中,SL58在第5輪次中被消除,SL57、SL67在第7輪次中被消除,TA578、TA678在第8輪次中才被消除,在第7輪次消除結束后獲得了最優(yōu)光譜指數(shù)子集,所以TA578、TA678是最優(yōu)光譜指數(shù)子集的成員,表明TA578、TA678在基于光譜指數(shù)的樹種分類中具有重要的作用,同時也說明樹種光譜曲線的面積指數(shù)優(yōu)于斜率指數(shù)。(6)基于24個紋理特征的樹種分類中,MEA-PC1、MEA-PC2、 EA-PC3是樹種分類中最重要的3個紋理特征；MEA-PC1、MEA-PC2、MEA-PC3、 ENT-PC2、ENT-PC1、DIS-PC2、SM-PC1、VAR-PC2、HOM-PC3、COR-PC1、 OR-PC3、CON-PC2、CON-PC1、VAR-PC3、 DIS-PC1、ENT-PC3是樹種分類中最優(yōu)紋理特征子集的16個成員；HOM-PC2、SM-PC2、 CON-PC3、HOM-PC1、DIS-PC3、COR-PC2、VAR-PC1、SM-PC3是導致最大似然發(fā)生休斯現(xiàn)象的8個紋理特征。(7)27維光譜指數(shù)分類的總體精度為72.4616%, Kappa系數(shù)為0.6787,較最優(yōu)光譜指數(shù)子集分類的總體精度(75.3962%)低2.9346%, Kappa系數(shù)(0.7126)低0.0339,表明在高維光譜指數(shù)分類中,最大似然存在著輕微的休斯現(xiàn)象；24個紋理特征分類的總體精度為40.5151%%, Kappa系數(shù)為0.3031,較最優(yōu)紋理特征子集分類的總體精度(81.1664%)低40.6513%, Kappa系數(shù)(0.7799)低0.4768,表明在高維紋理特征分類中,最大似然存在著嚴重的休斯現(xiàn)象。(8)本研究中,支持向量機分類的最高總體精度為84.6335%, Kappa系數(shù)為0.8204,從所有的分類中可以看出它對數(shù)據(jù)維數(shù)的增加不敏感,可以有效挖掘各個特征的有用信息,分類性能較穩(wěn)定。最大似然分類的最高總體精度為87.5310%,Kappa系數(shù)為0.8543,它對數(shù)據(jù)維數(shù)的增加較敏感,高維數(shù)據(jù)中會發(fā)生休斯現(xiàn)象,不能充分挖掘各個特征的有用信息,分類性能不穩(wěn)定。本研究構建的MLC-RFE消除了對最大似然分類精度的提高具有抑制作用的特征,規(guī)避了最大似然的休斯現(xiàn)象,使其在高維特征分類中的分類性能得到極大地提高,取得比支持向量機更高的分類精度。(9)樹種分類中,基于主成分的最高總體精度為63.9752%, Kappa系數(shù)0.5789;基于光譜波段的最高總體精度為74.0713%, Kappa系數(shù)0.6974；基于光譜指數(shù)的最高總體精度為75.3962%, Kappa系數(shù)0.7126；基于紋理特征的最高總體精度為81.1664%, Kappa系數(shù)0.7799；在光譜指數(shù)結合光譜波段中,最高總體精度為73.4274%, Kappa系數(shù)0.6900；在紋理結合光譜波段與主成分中,最高總體精度為86.3918%, Kappa系數(shù)0.8410；在紋理結合光譜指數(shù)與主成分中,最高總體精度為87.4319%, Kappa系數(shù)0.8532；在紋理結合光譜指數(shù)、光譜波段、主成分的混合特征中,最高總體精度為87.5310%, Kappa系數(shù)0.8543。除光譜指數(shù)結合光譜波段不能提高分類的總體精度與Kappa系數(shù)外,其余的特征組合類型均取得比單純基于主成分、光譜波段、光譜指數(shù)、紋理特征要高的總體精度與Kappa系數(shù),表明樹種分類中有效結合各特征類型,可以取得更好的分類結果。
[Abstract]:One of the problems yet to be solved through remote sensing technology to identify species, is one of the focus of attention of scholars. At present, tree image classification and auxiliary data based on high resolution has achieved certain results, but there were still many problems such as focus on the image information dimension narrow, image feature construction and selection is not scientific, the classifier does not solve the problem of Hughes phenomenon etc. This study takes Hohhot WorldView-2 image as data source, through image preprocessing, determine the classification tree, build image high-dimensional spectral index set, texture feature set, recursive feature elimination based on the maximum likelihood (MLC-RFE) to select important variables, avoid the maximum likelihood of the Hughes phenomenon, the optimal spectral index subset obtaining species classification and the texture feature subset. Combined with spectral band, spectral index, texture feature type, using the maximum likelihood combination of data For classification, the support vector machine classification results as a reference, the experimental results achieved better classification accuracy. The main results are as follows: (1) NDVI image in the blue roof, green plastic playground 2 objects and vegetation with NDVI is similar to the characteristics of city vegetation extraction caused interference, but there is a big difference in spectral curve three in the eight WorldView-2 band, the spectral angle classification can achieve complete separation between the three, part of the city to obtain accurate vegetation image. (2) the maximum likelihood of conifer, broadleaf trees and grasses are classified, the overall classification accuracy of WorldView-2 image of August was 93.9871%, Kappa coefficient is 0.9098, the overall the classification accuracy of QuickBird image of February is 96.6667%, Kappa coefficient was 0.9500. The results show that the selection of more special phase data source for conifer, broadleaf trees, grasses identification based on W (3). Species classification of orldView-2 spectral bands, the overall accuracy of maximum likelihood classification than the traditional 8 full band 4 band high 10.7231%, high Kappa coefficient 0.1253; support vector machine to complete the overall accuracy of classification than the traditional 8 band 4 band high 9.9183%, high Kappa coefficient 0.1158, show new WorldView-2 coast blue, yellow, red the 2 side, near infrared band plays an important role in species classification. (4) based on tree species classification of 27 dimensional spectral index, NDVI6, FDI2, NREB are the 3 most important species in the spectral index; NDVI6, FDI2, NREB, ARVI, NDVI5, NDVI2, GRVI, NYR, NDVI1, IPVI NPCI, R/RE, NDVI3, NIRNDVI, SAVI, NDVI7, NIR/GREEN, TA578, TA678, 19 members of the species classification index of optimal spectral subset; SL57, SL67, NDVI4, SL58, RVI, EVI, OSAVI, SL56 is the result of 8 spectral index of maximum likelihood Hughes phenomenon (5) in this study. The new 5 A spectral index SL57, SL67, SL58, TA578, TA678 and MLC-RFE in the selection of variables, SL58 is eliminated, SL57 in the fifth inning, SL67 is eliminated, TA578 in the seventh inning, TA678 was eliminated in the eighth round, seventh rounds of elimination in the optimal spectral index subset, after the end of TA578, TA678 is the optimal subset of the members, the spectral index showed that TA578 and TA678 play an important role in species classification based on spectral index, but also shows the species spectral curve area index is better than the slope index. (6) based on tree species classification of 24 texture features, MEA-PC1, MEA-PC2, EA-PC3 is the 3 most important species in texture feature the classification of MEA-PC1, MEA-PC2, MEA-PC3; ENT-PC2, ENT-PC1, DIS-PC2, SM-PC1, VAR-PC2, HOM-PC3, COR-PC1, OR-PC3, CON-PC2, CON-PC1, VAR-PC3, DIS-PC1, ENT-PC3 is the 16 member optimal texture feature subset in the classification of species; HOM-PC2, SM-P C2, CON-PC3, HOM-PC1, DIS-PC3, COR-PC2, VAR-PC1, SM-PC3 are 8 texture features of the maximum likelihood Hughes phenomenon caused. (7) the overall accuracy of 27 dimensional spectral classification index is 72.4616%, Kappa coefficient was 0.6787, compared with the overall accuracy of the optimal spectral index subset classification (75.3962%) 2.9346%, Kappa (coefficient of 0.7126 0.0339) low, show that in high dimensional spectral index classification, maximum likelihood there is a slight Hughes phenomenon; the overall accuracy of the 24 texture feature classification 40.5151%%, Kappa coefficient is 0.3031, the overall accuracy compared with the optimal texture feature subset classification (81.1664%) 40.6513%, Kappa coefficient (0.7799) shows that in the 0.4768 low, high dimensional texture classification, maximum likelihood is a serious phenomenon of Hughes. (8) in this study, the highest overall accuracy of support vector machine classification is 84.6335%, Kappa coefficient is 0.8204, from which all can be seen in the classification of it Not sensitive to the increase of data dimensionality, useful information can effectively tap the various features, the classification performance is stable. The highest overall accuracy of maximum likelihood classification is 87.5310%, Kappa coefficient is 0.8543, it is sensitive to the data dimension increases, Hughes phenomenon in the high dimensional data, useful information can not fully excavate various features, classification the performance is not stable. The construction of the MLC-RFE elimination characteristics have inhibitory effect on the maximum likelihood classification to improve the accuracy of the maximum likelihood, to avoid the Hughes phenomenon, the classification in high dimensional feature classification can be greatly improved, higher classification accuracy than support vector machine (9 species). In classification, the highest overall accuracy based on principal component was 63.9752%, Kappa coefficient is 0.5789; the highest overall accuracy based on band 74.0713%, Kappa coefficient is 0.6974; the highest total based on spectral index Body precision was 75.3962%, Kappa coefficient is 0.7126; the highest overall accuracy based on texture feature is 81.1664%, Kappa coefficient is 0.7799; in the spectral index and spectral bands, the highest overall accuracy is 73.4274%, Kappa coefficient is 0.6900; in texture and spectral bands with principal components, the highest overall accuracy is 86.3918%, Kappa coefficient is 0.8410; in the combination of texture the spectral index and principal components, the highest overall accuracy is 87.4319%, Kappa coefficient is 0.8532; combined with the spectral index, the texture spectrum band, mixing characteristics of principal components, the highest overall accuracy is 87.5310%, Kappa coefficient 0.8543. in spectral index and spectral bands can improve the overall accuracy and Kappa coefficient classification, types and characteristics of the rest of the combination are better than only based on principal component spectral bands, spectral index, texture features to the overall accuracy and Kappa coefficient is high, the tree species classification Better classification results can be obtained by effectively combining each characteristic type.

【學位授予單位】：內蒙古農業(yè)大學
【學位級別】：博士
【學位授予年份】：2016
【分類號】：S731.2;S771.8

【參考文獻】

相關期刊論文 前10條

1 吳滿意;付冬暇;王占宏;田懷啟;張光輝;于金芝;;資源三號衛(wèi)星影像融合優(yōu)化方法探討[J];測繪科學;2016年06期

2 闞煜;龔紹琦;劉朝順;;HY-1B/COCTS熱紅外波段的交叉輻射定標方法研究[J];地理與地理信息科學;2015年06期

3 劉錕;付晶瑩;李飛;;高分一號衛(wèi)星4種融合方法評價[J];遙感技術與應用;2015年05期

4 劉懷鵬;安慧君;王冰;張秋良;;基于遞歸紋理特征消除的WorldView-2樹種分類[J];北京林業(yè)大學學報;2015年08期

5 王璐;范文義;;基于高光譜遙感數(shù)據(jù)的森林優(yōu)勢樹種組識別[J];東北林業(yè)大學學報;2015年05期

6 田甜;范文義;盧偉;肖湘;;面向對象的優(yōu)勢樹種類型信息提取技術[J];應用生態(tài)學報;2015年06期

7 王樂;牛雪峰;魏斌;陳立春;;遙感影像融合質量評價方法研究[J];測繪通報;2015年02期

8 林海軍;張繪芳;高亞琪;李霞;楊帆;周艷飛;;基于馬氏距離法的荒漠樹種高光譜識別[J];光譜學與光譜分析;2014年12期

9 任國貞;江濤;;基于灰度共生矩陣的紋理提取方法研究[J];計算機應用與軟件;2014年11期

10 潘鑫;楊英寶;張竹林;劉會芬;;資源三號衛(wèi)星影像融合方法的比較與評價[J];地理空間信息;2014年05期

相關博士學位論文 前8條

1 何飛;基于Gabor濾波的虹膜多特征提取及融合識別方法研究[D];吉林大學;2015年

2 夏瑜;基于結構的紋理特征及應用研究[D];中國科學技術大學;2014年

3 樓雄偉;支持向量機的核方法研究及其在森林火災視頻識別中的應用[D];浙江工業(yè)大學;2014年

4 劉高峰;極化SAR圖像特征提取與分類方法研究[D];西安電子科技大學;2014年

5 王凱;基于多特征融合的高光譜影像地物精細分析方法研究[D];武漢大學;2013年

6 凌成星;Worldview-2八波段影像支持下的濕地信息提取與地上生物量估算研究[D];中國林業(yè)科學研究院;2013年

7 王彩玲;基于相位信息的圖像匹配技術及應用研究[D];南京理工大學;2012年

8 譚炳香;高光譜遙感森林類型識別及其郁閉度定量估測研究[D];中國林業(yè)科學研究院;2006年

相關碩士學位論文 前7條

1 霍海利;圖像配準關鍵算法研究[D];北京理工大學;2015年

2 劉懷鵬;基于WorldView-Ⅱ數(shù)據(jù)的呼和浩特市綠化樹種分類研究[D];內蒙古農業(yè)大學;2013年

3 付志鵬;基于WorldView-2影像的分類及建筑物提取研究[D];浙江大學;2011年

4 張劍峰;呼和浩特市建成區(qū)道路綠地樹種現(xiàn)狀分析及評價[D];內蒙古農業(yè)大學;2010年

5 吳喜慧;基于高分辨率遙感影像的楊凌區(qū)土地利用/覆被變化研究[D];西北農林科技大學;2010年

6 李紅;地物光譜特征分析及其在礦化蝕變信息提取中的應用研究[D];中南大學;2010年

7 吳林巧;基于QuickBird影像的森林資源分類研究[D];南京林業(yè)大學;2009年

，

本文編號：1397180