請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/21335
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 徐百輝 | |
dc.contributor.author | Ying-Ying Cheng | en |
dc.contributor.author | 鄭盈盈 | zh_TW |
dc.date.accessioned | 2021-06-08T03:31:23Z | - |
dc.date.copyright | 2019-08-15 | |
dc.date.issued | 2019 | |
dc.date.submitted | 2019-08-13 | |
dc.identifier.citation | 徐百輝,曾義星,2000。高光譜影像特徵萃取方法之探討,航測與遙測學刊,5(2):1-14。
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,國立成功大學測量工程學系博士論文,台南。 曾義星,2009。高光譜影像分析及應用整合型研究-子計畫一:高光譜資料之收集、分析、特徵擷取及分類之研究(I),國科會研究報告,成功大學測量工程學系(所),台南。 練秋生,石保順,陳書貞,2015。字典學習模型、算法及其應用研究進展,自動化學報,41(2):240-260。 Aharon, M., Elad, M., and Bruckstein, A. (2006). K-SVD: An Algorithm For Designing Overcomplete Dictionaries for Sparse Representation. IEEE Transaction on Signal Process, 54: 4311-4322. Bellman, R. (1961). Adaptive Control Processes: A Guided Tour. Princeton University Press. Candès, E. J., Romberg, J. and Tao, T. (2006). Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information. IEEE Trans. Inf. Theory, 52(2), pp. 489–509. Chen, Y., N. M. Nasrabadi and T. D. Tran. (2011). Hyperspectral Image Classification Using Dictionary-Based Sparse Representation. IEEE Transactions on Geoscience and Remote Sensing, 49(10): 3973-3985. Donoho, D. L. (2006). Compressed Sensing. IEEE Trans. Inf. Theory, 52(4):1289-1306. Engan, K., Aase, S.O., Husoy, J.Hakon. (1999). Method of optimal directions for frame design. In ICASSP '99: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing. Washington, DC, USA: IEEE, 5: 2443-2446. Jolliffe, I. (1986). Principal Component Analysis, New York: Springer Verlag. Lee, C. and Landgrebe, D. A. (1993). Analyzing High-Dimensional Multisepctral Data. IEEE Transactions on Geoscience and Remote Sensing, 31: 792-800. Lillesand, T.M., Kiefer, R.W. and Chipman, J. (2015). Remote Sensing and Image Interpretation, 7th Ed. John Wiley & Sons, New York. Natarajan, B. K. (1995). Sparse approximate solutions to linear systems. SIAM J.Comput, 24(2):227-234. Plaza, A., Plaza, J. and Vegas, H. (2010). Improving the Performance of Hyperspectral Image and Signal Processing Algorithms Using Parallel, Distributed and Specialized Hardware-Based Systems. Journal of Signal Processing Systems, 61(3):293-315. Ready, P. J. and Wintz, P. A. (1973). Information extraction, SNR improvement, and data compression in multispectral imagery. IEEE Transactions on Communications, Con-21(10): 1123-1130. Sami ul Haq, Q., Shi, L., Tao, L., & Yang, S. (2010). Hyperspectral data classification via sparse representation in homotopy. Paper presented at the The 2nd International Conference on Information Science and Engineering (ICISE), Hangzhou, China. Schowengerdt, R. A. (1997). Remote Sensing: Models and Methods for Image Processing. Academic Press, New York. Shi, J., Ren, X., Dai, G., Wang, J. and Zhang, Z. (2011). A non-convex relaxation approach. to sparse dictionary learning. in Proc. IEEE Conf. Comput. Vis. Pattern Recognit (CVPR), pp. 1809–1816. Sterckx, S., Knaeps, E., Bollen, M., Trouw, K., and Houthuys, R. (2006). Operational Remote Sensing Mapping of Estuarine Suspended Sediment Concentrations (ORMES). Hydro06—Evolutions in Hydrography, Antwerp, Belgium. Sun, X., Qu, Q., Nasrabadi, N. M., and Tran. T. D. (2014). Structured Priors for Sparse-Representation-Based Hypersepctral Image Classification. Geoscience and Remote Sensing Letters, IEEE, 11(7): 1235-1239. Tadjudin, S., & Landgrebe, D. (1998). Classification of High Dimensional Data with Limited Training Sample. Ph.D. thesis, School of Electrical Engineering and Computer Science, Purdue University. Wang, Z., Liu, J., Xue, J. (2017). Joint sparse model-based discriminative K-SVD for hyperspectral image classification. Signal Processing, 133: 144-155. Yang, M., Zhan, D., Feng, X.C., Zhang, D. (2011). Fisher discrimination dictionary learning for sparse representation. In: Proceedings of the 2011 IEEE International Conference on Computer Vision. Barcelona, Spain: IEEE. 543−550. Zhang, Z., Xu, Y., Yang, J., Li, X., & Zhang, D. (2015). A Survey of Sparse Representation: Algorithms and Applications. IEEE Access, 3: 490-530. Zhang, E., Zhang, X., Jiao, L., Li, L., & Hou, B. (2016). Spectral–Spatial Hyperspectral Image Ensemble Classification via Joint Sparse Representation. Pattern Recognition, 59: 42-54. Zhang, Q., Li, B.Q. (2010). Discriminative K-SVD for dictionary learning in face. recognition. In: Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, USA: IEEE. 2691-2698. Zhang, Z., Xu, Y., Yang, J., Li, X., & Zhang, D. (2015). A Survey of Sparse Representation: Algorithms and Applications. IEEE Access, 3: 490-530. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/21335 | - |
dc.description.abstract | 自我學習提升效能之機器學習演算法逐漸普及於遙測影像資料處理及分析,機器學習的優勢在於不需預先了解全部資料的特性,且資料分佈不必為常態分布,較能描述遙測影像資料之實際分布。具高維度特性的資料,如高光譜影像,其重要資訊主要集中在較低維度的子空間中;此外,同類像元通常會近似分布於同一個低維度子空間中。如何降低資料維度並進行分類,成為高光譜影像分析的主要研究議題。近十年來,大量研究致力於以稀疏表示方法進行高光譜影像分類。稀疏表示在訊號重建方面有著良好的效能,其可處理具稀疏特性的資料,因此很適合運用於高光譜影像之處理及分析。
本研究將以聯合稀疏表示為基礎,提出一個適合高光譜影像分類之方法。在進行研究時,主要可分為三部分進行探討:一、字典之建構,透過機器學習演算法,利用已知訊號之訓練樣本獲得字典。二、稀疏係數最佳解之求解,以正交匹配追逐法等進行稀疏係數之求解。三、建立聯合稀疏表示之分類模型,同時整合空間及光譜資訊至稀疏表示演算法的目標函數中,建立以聯合稀疏表示為基礎的影像分類方法,期能提升高光譜影像分類之效能及準確性。 | zh_TW |
dc.description.abstract | Machine learning algorithms using self-learning to improve performance have become increasingly popular in the processing and analysis of remote sensing image data. The advantage of machine learning is that it is not necessary to know the prior characteristics of data in advance, and the data distribution does not have to be normally distributed, so it is more able to describe the actual distribution of remote sensing image data. Most important information of high-dimensional data (e.g. hyperspectral images) is mainly clustered in low-dimensional subspace. Moreover, pixels belonging to the same class are usually distributed in the same low-dimensional subspace. Therefore, how to reduce the dimensionality for classification has become the major issue for hyperspectral image analysis. Considerable researches have been dedicated to hyperspectral image classification via sparse representation methods over the past decade. Sparse representation has shown good performance in signal reconstruction and can be used to process data with sparse properties, so it is quite suitable for hyperspectral images analysis.
On the basis of sparse representation method, the paper consists of three main parts for discussion. First, the method for dictionary construction will be introduced. With machine learning algorithm, dictionaries can be obtained by training samples of provided spectral signal. Second, the solutions for sparse coefficients optimization, such as orthogonal matching pursuit is tested for experiment analysis. Third, the model of joint sparse representation for hyperspectral image classification will be put forward. In the proposed model, the spectral and spatial information are integrated into the joint sparse representation simultaneously to improve the efficiency and accuracy of the hyperspectral image classification. | en |
dc.description.provenance | Made available in DSpace on 2021-06-08T03:31:23Z (GMT). No. of bitstreams: 1 ntu-108-R06521806-1.pdf: 2956072 bytes, checksum: ab4b1959073d24592abee2ec0047c98f (MD5) Previous issue date: 2019 | en |
dc.description.tableofcontents | 口試委員會審定書 #
誌謝 i 中文摘要 ii ABSTRACT iii 目錄 iv 圖目錄 vi 表目錄 vii 第一章 緒論 1 1.1 研究動機與目的 1 1.2 論文架構 2 第二章 理論基礎與文獻回顧 3 2.1 高光譜影像 3 2.2 高光譜影像特徵萃取及分類 6 2.2.1 基於統計理論之特徵萃取方法 6 2.2.2 基於頻率分析之特徵萃取方法 7 2.3 稀疏表示及其應用 8 2.3.1 稀疏表示理論 8 2.3.2 字典之建構 10 2.4 稀疏表示於高光譜影像分類之應用 12 第三章 研究方法 14 3.1 字典建構 15 3.1.1 類別子字典 15 3.1.2 單一像元光譜訊號之稀疏表示 15 3.2 光譜訊號之重建 16 3.2.1 光譜訊號之稀疏表示 16 3.2.2 加入正規化參數之稀疏表示 16 3.3 光譜訊號之分類 17 3.4 字典學習 17 3.4.1 MOD 17 3.4.2 K-SVD 18 3.5 結合光譜與空間資訊之聯合稀疏表示模型 19 3.5.1 聯合稀疏表示 19 3.5.2 加入約制條件之聯合稀疏表示 20 3.6 採用之稀疏表示模型 20 3.7 精度評估方式 21 第四章 實驗及成果分析 23 4.1 實驗資料 23 4.1.1 實驗資料(ㄧ) 23 4.1.2 實驗資料(二) 24 4.2 實驗方法與成果分析 25 4.2.1 實驗方法(ㄧ) 25 4.2.2 實驗(ㄧ)成果與分析 26 4.2.3 實驗(ㄧ)訓練樣本比率 27 4.2.4 實驗(ㄧ)模型參數 29 4.2.5 實驗方法(二) 33 4.2.6 實驗(二)成果與分析 34 4.2.7 實驗(二)訓練樣本比率 37 4.2.8 實驗(二)固定訓練樣本數 40 4.2.9 實驗(二)模型參數 43 4.2.10 實驗(二)稀疏度 57 4.2.11 實驗(二)字典原子數 58 第五章 結論與建議 61 REFERENCE 63 | |
dc.language.iso | zh-TW | |
dc.title | 結合光譜及空間資訊之聯合稀疏表示應用於高光譜影像分類 | zh_TW |
dc.title | Hyperspectral image classification via integration of joint sparse representation with spectral and spatial information | en |
dc.type | Thesis | |
dc.date.schoolyear | 107-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 邱式鴻,黃金聰 | |
dc.subject.keyword | 機器學習,稀疏表示,字典學習,高光譜影像,影像分類, | zh_TW |
dc.subject.keyword | Machine Learning,Sparse representation,Dictionary learning,Hyperspectral imagery,Image classification, | en |
dc.relation.page | 65 | |
dc.identifier.doi | 10.6342/NTU201903132 | |
dc.rights.note | 未授權 | |
dc.date.accepted | 2019-08-13 | |
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-108-1.pdf 目前未授權公開取用 | 2.89 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。