請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/43498完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 徐百輝(Pai-Hui Hsu) | |
| dc.contributor.author | Ting-Yi Li | en |
| dc.contributor.author | 李庭誼 | zh_TW |
| dc.date.accessioned | 2021-06-15T02:22:28Z | - |
| dc.date.available | 2012-08-22 | |
| dc.date.copyright | 2011-08-22 | |
| dc.date.issued | 2011 | |
| dc.date.submitted | 2011-08-17 | |
| dc.identifier.citation | Bellman, R., 1961. Adaptive control processes - A guided tour: Princeton University Press.
Bharati, M. H., Liu, J. J., and MacGregor, J. F., 2004. Image texture analysis: methods and comparisons. [doi: DOI: 10.1016/j.chemolab.2004.02.005]. Chemometrics and Intelligent Laboratory Systems, 72(1): 57-71. Chang, T., Kuo, C. C. J., and Lin, Y.-C., 1993. Texture segmentation using wavelet packets, San Diego, CA, USA. Clarke, K. C., 1986. Computation of the fractal dimension of topographic surfaces using the triangular prism surface area method. [doi: DOI: 10.1016/0098-3004(86)90047-6]. Computers & Geosciences, 12(5): 713-722. Coburn, C. A., and Roberts, A. C. B., 2004. A multiscale texture analysis procedure for improved forest stand classification. International Journal of Remote Sensing, 25(20): 4287 - 4308. Daubechies, I., 2004. Ten lectures on wavelets: Society for industrial and applied mathematics. Fukunaga, K., 1990. Introduction to Statistical Pattern Recognition: Academic Press. Galloway, M. M., 1975. Texture analysis using gray level run lengths. [doi: DOI: 10.1016/S0146-664X(75)80008-6]. Computer Graphics and Image Processing, 4(2): 172-179. Gonzalez, R. C., and Woods, R. E., 2002. Digital image processing. Upper Saddle River, N.J.: Prentice Hall. Haralick, R. M., Shanmugam, K., and Dinstein, I. H., 1973. Textural Features for Image Classification. Systems, Man and Cybernetics, IEEE Transactions on, 3(6): 610-621. Hsu, P.-H., 2007. Feature extraction of hyperspectral images using wavelet and matching pursuit. [doi: DOI: 10.1016/j.isprsjprs.2006.12.004]. ISPRS Journal of Photogrammetry and Remote Sensing, 62(2): 78-92. Hughes, G., 1968. On the mean accuracy of statistical pattern recognizers. Information Theory, IEEE Transactions on, 14(1): 55-63. Kayitakire, F., Hamel, C., and Defourny, P., 2006. Retrieving forest structure variables based on image texture analysis and IKONOS-2 imagery. [doi: DOI: 10.1016/j.rse.2006.02.022]. Remote Sensing of Environment, 102(3-4): 390-401. Landgrebe, D. A. (2001). Analysis of Multispectral and Hyperspectral Image Data. In Edward M. Mikhail, James S. Bethel & J. Chris McGlone (Eds.), Introduction to Modern Photogrammetry: John Wiley and Sons, Inc. . Lee, C., and Landgrebe, D. A., 1993a. Analyzing high-dimensional multispectral data. Geoscience and Remote Sensing, IEEE Transactions on, 31(4): 792-800. Lee, C., and Landgrebe, D. A., 1993b. Feature Extraction and Classification Algorithms for High Dimensional Data. Unpublished PhD Dissertation, Purdue University, West Lafayette, Indiana. Mallat, S. G., 1989. A theory for multiresolution signal decomposition: the wavelet representation. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 11(7): 674-693. Manian, V., and Jimenez, L. O., 2007. Land cover and benthic habitat classification using texture features from hyperspectral and multispectral images. Journal of Electronic Imaging, 16(2): 023011-023012. Marceau, D. J., P. J. Howarth, J. M. Dugois, and D. J. Gratton. 1990. Evaluation of the grey-level co-occurrence matrix method for land-cover classification using SPOT. IEEE Transaction on Geosciences and Remote Sensing, imagery, 28: 513-519. Materka, A., and Strzelecki, M. (1998). Texture Analysis Methods–A Review (No. COST B11 report): Technical University of Lodz. . Mockler, R. J., 1992. Developing knowledge-based systems using an expert systems shell. New York: Maxwell Macmillan. Oruc, M., Marangoz, A. M., and Buyuksalih, G. (2004). Comparison of pixel-based and object-oriented classification approaches using LANDSAT-7 ETM spectral bands. Paper presented at the Proceeding of the ISPRS 2004 Annual Conference. Ouma, Y. O., Ngigi, T. G., and Tateishi, R., 2006. On the optimization and selection of wavelet texture for feature extraction from high-resolution satellite imagery with application towards urban-tree delineation. International Journal of Remote Sensing, 27(1): 73-104. Schowengerdt, R. A., 1997. Remote Sensing, Models and Methods for Image Processing (Second ed.): Academic Press. Shaw, G. A., 2003. Spectral imaging for remote sensing Lincoln Laboratory Journal, 14(1): 3-28. Sonka, M., 1998. Image processing:analysis and machine vision ( 2nd. ed. ed.). United States of America. Swain, P. H., and Davis, S. M., 1978. Remote sensing: the quantitative approach: McGraw-Hill Inc. Tadjudin, S., and Landgrebe, D. A., 1998. Classification of high dimensional data with limited training samples. West Lafayette: Purdue University. Zhang, L., and Huang, X., 2010. Object-oriented subspace analysis for airborne hyperspectral remote sensing imagery. [doi: DOI: 10.1016/j.neucom.2009.09.011]. Neurocomputing, 73(4-6): 927-936. 沈育佳，1998。都會區空載多光譜掃瞄影像紋理分析之研究，碩士論文，國立中興大學。 徐百輝，2003。小波轉換應用於高光譜影像光譜特徵萃取之研究，博士論文，國立成功大學。 徐百輝與張嘉玳，2010。物件導向分類演算法於衛星影像分析之應用: 中央大學前瞻通訊實驗室九十九年度專案研究計畫。 張鈞凱，2007。高光譜影像立方體紋理特徵之三維計算，碩士論文，國立中央大學。 莊政斌，2004。影像分割技術於高解析衛星影像分類之應用，碩士論文，國立中央大學。 莊雲翰，2002。結合影像區塊及知識庫分類之研究-以ikonos衛星影像為例，碩士論文，國立中央大學。 陳彥宏，2004。運用紋理資訊輔助高解析度衛星影像於都會區水稻田萃取之研究，碩士論文，逢甲大學。 趙錫民，2000。結合塔像與紋理分類之地物萃取法，測量工程，第四十二卷(第二期): 第1-22頁。 鄭雅文，2006。高解析度衛星影像分類應用於國土利用調查之研究，碩士論文，國立交通大學。 | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/43498 | - |
| dc.description.abstract | 高光譜影像具有數十至數百個波段數，光譜資訊豐富且細緻，然而於實際應用時卻容易面臨資訊過多處理不易，以及分類時常易發生訓練樣本數不足的問題。另一方面，隨著遙測影像空間解析度之提升，影像中通常含有豐富之紋理（texture）資訊，能夠有效提升影像之分類精度，例如GLCM（gray level co-occurrence matrix）即為傳統常用的統計紋理分析方式，然而其卻有計算量大，計算時須降低影像色階數而導致影像光譜資訊流失等問題，故不適合用於高光譜影像之紋理分析。另外紋理的計算通常係以影像區塊或影像物件為基本單元，相較於傳統逐像元分類（pixel-based classification）方法，物件式的影像分析方法（object-based image analysis, OBIA）不會有邊緣破碎及椒鹽現象等問題。為有效解決上述有關高光譜影像分類所面臨之問題，本研究針對高光譜影像提出一套結合光譜特徵與空間紋理特徵的物件導向分類流程。首先，對高光譜影像進行小波光譜分解以縮減維度，萃取出數個有效的光譜特徵，接著對所萃取出之光譜特徵進行空間紋理特徵之計算，得到混和特徵，並以混合特徵選取之方式，選出適於分類的混合特徵組，最後，針對混合特徵組進行物件導向分類。實驗證實此套影像分類流程能夠達到約94%的分類精度，並且值得注意的是，此分類處理流程能夠大幅提升類別間分離度低的影像之光譜特徵萃取後的分類精度，成果顯示最高可提升分類精度約達20%。 | zh_TW |
| dc.description.abstract | The purpose of feature extraction is to reduce the dimensionality of hyperspectral images to solve classification problems caused by limited training samples. In this study, a hybrid feature extraction method which integrates spectral features and spatial features simultaneously is proposed. Firstly, the spectral-feature images are calculated along the spectral dimension of hyperspectral images using wavelet decomposition because wavelet has been proven effective in extracting spectral features.
Secondly, ten different kinds of spatial-features, which are calculated along the two spatial dimensions of hyperspectral images, are implemented on the wavelet spectral-feature images. Then a feature selection method based on the optimization of class separability is performed on the extracted spectral-spatial features to get the hybrid features which could be suitable for classification applications. In this study, the object-based image analysis (OBIA) is used for hyperspectral image classification. The experiment results showed that the overall accuracy for the classification of a real hyperspectral data set using our proposed approach could reach approximately 94%. Moreover, it is worth mentioning that the hybrid features and OBIA classification could significantly rise the overall accuracy of hyperspectral images which contain poor separability between classes, after the spectral features were extracted. The experiment result also showed that the overall accuracy would go up by 20% by using our proposed approach on hyperspectral images with poor class separability. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-15T02:22:28Z (GMT). No. of bitstreams: 1 ntu-100-R98521111-1.pdf: 5389791 bytes, checksum: 60a43a6f73da9862e2605127a5a5c327 (MD5) Previous issue date: 2011 | en |
| dc.description.tableofcontents | 摘要 I
ABSTRACT II 目錄 III 圖目錄 VI 表目錄 IX 第一章緒論 1 1.1 研究背景 1 1.2 研究動機與目的 3 1.3 研究架構 5 第二章高光譜影像之光譜特徵萃取 7 2.1 高光譜影像簡介 7 2.2 高光譜影像所面臨之問題及解決方法 9 2.2.1 維度的詛咒 9 2.2.2 維度縮減 11 2.3 光譜特徵萃取 11 2.3.1 常見之光譜特徵萃取方式 12 2.3.2 小波轉換 13 2.3.3 小波光譜分解 15 2.4 光譜特徵萃取之實驗成果與分析 19 第三章空間紋理特徵萃取 22 3.1 紋理 22 3.1.1 紋理之定義 22 3.1.2 紋理特徵對影像分類之影響 24 3.1.3 傳統GLCM紋理特徵之計算方式 26 3.2 GLCM之實驗成果與分析 32 3.2.1 GLCM應用於一般影像 32 3.2.2 GLCM應用於高光譜影像 36 3.3 混合特徵選取及分類 38 3.4 混合特徵選取之實驗成果與分析 42 3.4.1 混合特徵選取及分類 43 3.4.2 不同訓練樣本數對於混合特徵分類成果之影響 45 3.4.3 空間紋理特徵及其選取之必要性的驗證 47 第四章物件導向分類 53 4.1 物件導向分類與逐像元分類方法之比較 53 4.2 紋理特徵結合物件導向分類之應用 56 4.3 物件導向分類之流程 57 4.3.1 影像分割 59 4.3.2 物件特徵萃取 63 4.3.3 建立分類規則 65 4.3.4 分類 67 4.4 物件導向分類之實驗成果與分析 68 4.4.1 影像分割 68 4.4.2 建立物件導向分類知識庫 71 4.4.3 物件導向分類成果 76 第五章測試實驗與成果討論 78 5.1 影像資訊 78 5.2 訓練樣本與測試樣本資訊 79 5.3 光譜特徵萃取 80 5.4 混合特徵選取 82 5.4.1 不同訓練樣本數對於混合特徵選取成果之影響 83 5.4.2 空間紋理特徵及其選取必要性之驗證 85 5.5 物件導向分類 89 5.5.1 影像分割 89 5.5.2 建立物件導向分類知識庫 91 5.5.3 物件導向分類成果 93 第六章結論與建議 95 參考文獻 98 附錄A 影像分類成果檢核 102 附錄B 第一張實驗影像之分類知識庫規則 105 | |
| dc.language.iso | zh-TW | |
| dc.subject | 空間紋理特徵 | zh_TW |
| dc.subject | 高光譜影像 | zh_TW |
| dc.subject | 光譜小波分解 | zh_TW |
| dc.subject | 物件導向分類 | zh_TW |
| dc.subject | Object-Based Image Analysis (OBIA) | en |
| dc.subject | Hyperspectral Remote Sensing | en |
| dc.subject | Classification | en |
| dc.subject | Hybrid Feature Selection | en |
| dc.title | 結合光譜與空間特徵之高光譜影像物件分類 | zh_TW |
| dc.title | Hybrid Feature Extraction for Object-based Hyperspectral Image Classification | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 99-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 趙鍵哲,張智安,王聖鐸 | |
| dc.subject.keyword | 高光譜影像,光譜小波分解,空間紋理特徵,物件導向分類, | zh_TW |
| dc.subject.keyword | Hyperspectral Remote Sensing,Hybrid Feature Selection,Object-Based Image Analysis (OBIA),Classification, | en |
| dc.relation.page | 106 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2011-08-17 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 土木工程學研究所 | zh_TW |
| 顯示於系所單位： | 土木工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-100-1.pdf 未授權公開取用 | 5.26 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。