跳到主要內容

臺灣博碩士論文加值系統

(3.236.124.56) 您好!臺灣時間:2021/07/30 04:48
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:許智傑
研究生(外文):Chih-Chieh Hsu
論文名稱:光譜-空間分類法結合低通濾波器於高光譜影像辨識
論文名稱(外文):Spectral-Spatial Classification with Low-Pass Filters to pattern recognition of Hyperspectral Imagery
指導教授:蘇東青蘇東青引用關係
指導教授(外文):Tung-Ching Su
口試委員:楊明德劉霈洪集輝
口試委員(外文):Ming-Der YangPei LuJi-Hwei Horng
口試日期:2012-06-21
學位類別:碩士
校院名稱:國立金門大學
系所名稱:土木與工程管理學系碩士班
學門:工程學門
學類:土木工程學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:中文
論文頁數:128
中文關鍵詞:高光譜影像雜訊濾波特徵影像光譜-空間分類
外文關鍵詞:Hyperspectral imageryNoise filtersEigenimageSpectral-spatial classification
相關次數:
  • 被引用被引用:0
  • 點閱點閱:270
  • 評分評分:
  • 下載下載:79
  • 收藏至我的研究室書目清單書目收藏:0
高光譜影像因含有豐富光譜資訊,已廣泛應用於許多領域,然而高維度光譜資訊相應有限分類物種,使得影像分類工作成為挑戰。相關文獻指出,現有影像分類技術對於高光譜影像上空間結構較小物種,無法有效偵測並分類,因此本研究提出光譜-空間分類法結合低通濾波進行高光譜影像辨識。該方法主要目的有二,其ㄧ為提升整體分類準確度,另ㄧ為大、小空間結構物種均可有效被偵測及分類。本研究所提光譜-空間分類法涉及:最小噪聲分離(Minimum Noise Fraction, MNF)、數學形態影像梯度計算(Gradient Calculation Based on Mathematical Morphology)、分水嶺分割(Watershed Segmentation)、以及支持向量機(Support Vector Machine, SVM)等影像處理與分類技術。為有效降低物種分類時受影像雜訊之干擾,本研究對原始影像及最小噪聲分離處理後之影像,設計八組雜訊濾波組合以找出較佳雜訊濾波處理方式。研究結果顯示,依據最小噪聲分離所獲得的特徵影像進行分類成果後處理,可有效改善傳統僅考慮像元資訊之分類方式,分類準確度由84.08%提升至87.42%。利用低通濾波器輔助光譜-空間分類法進行分類,可有效降低胡椒鹽效應,整體分類準確度由87.42%進一步提升至91.5%。此外,空間結構較小物種其分類準確度可介於75%至80%之間,顯示本研究所提光譜-空間分類法結合低通濾波處理,可適用於高光譜影像分類。
Recently several spectral-spatial classification methods had been presented and applied to pattern recognition of hyperspectral imagery. However, the present methods are especially suitable for classifying images with large spatial structures in spite of the derived classification accuracies of above 90%. To classify hyperspectral images with larger as well as smaller spatial structures, a novel spectral-spatial classification method was presented and tested on an Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) image with 145×145 pixels and 220 bands. Firstly, the AVIRIS image was implemented a spectral mixture analysis using minimum Low-Pass fraction (MNF). Based on the obtained n-dimensional eigenimage, support vector machine (SVM) was used to classify the AVIRIS image. Simultaneously, the eigenimage was calculated the mathematical morphology-based image gradients for the n dimensions so to obtain n watershed segmentation images. Finally, the SVM classification map was post-processed based on the n watershed segmentation images to derive new ones with better performances. In addition to the spectral-spatial classification method, this thesis also compared with the different Low-Pass filter approaches, which were applied to the AVIRIS map and the n-dimensional eigenimage, to find out the best approach to improve the SVM classification or the post-processing results. The proposed spectral-spatial classification method can improve the overall accuracy of the traditional classification, such as SVM, from 84.08% to 87.42%. Moreover, taking the Low-Pass filters into consideration of the spectral-spatial classification method can further improve the overall accuracy of 87.42% to 91.5%, in which the accuracies of the smaller spatial structures range between 75% and 80%. Thus, this thesis verifies that the proposed spectral-spatial classification method with Low-Pass filters has the robust capability to pattern recognition of hyperspectral imagery.
摘要 ............................................................................................................................................ I
ABSTRACT .............................................................................................................................. II
致謝 ......................................................................................................................................... III
目錄 ......................................................................................................................................... IV
表目錄 ..................................................................................................................................... VI
圖目錄 .................................................................................................................................. VIII
第一章 緒論 .............................................................................................................................. 1
1.1 前言 ................................................................................................................................. 1
1.2 研究動機與目的 .............................................................................................................. 2
1.3 論文架構 .......................................................................................................................... 3
第二章 相關研究與文獻探討 .................................................................................................. 5
2.1 高光譜簡介與應用範圍 .................................................................................................. 5
2.2 光譜混合 .......................................................................................................................... 7
2.2.1 何謂光譜混合 .......................................................................................................... 7
2.2.2 光譜混合分析 ........................................................................................................... 8
2.3 影像分類技術 .................................................................................................................. 9
2.4 光譜空間分類 ................................................................................................................ 12
2.5 高光譜影像濾波處理 .................................................................................................... 13
2.6 總結 ............................................................................................................................... 13
第三章 研究方法與流程 ........................................................................................................ 15
3.1 雜訊濾波(NOISE FILTER) ................................................................................................ 18
3.1.1 均值濾波器(Mean Filter) ....................................................................................... 19
3.1.2 中值濾波器(Median Filter) .................................................................................... 20
3.2 最小噪聲分離(MINIMUM NOISE FRACTION) ................................................................. 21
3.3 數學形態影像梯度計算 ................................................................................................ 23
3.4 分水嶺影像分割 ............................................................................................................ 25
3.5 支持向量機(SUPPORT VECTOR MACHINE) .................................................................... 27
3.6 影像分類後處理 ............................................................................................................ 30
第四章 實驗結果 .................................................................................................................... 31
4.1 MNF 光譜混合分析 ....................................................................................................... 32
4.2 SVM 初始分類結果 ....................................................................................................... 34
4.3 影像梯度計算與分水嶺分割 ........................................................................................ 39
4.4 影像分類後處理及準確度評估 .................................................................................... 42
4.4.1 未採用低通濾波處理 ............................................................................................ 42
4.4.2 採用低通濾波處理 ................................................................................................ 47
4.4.3 總結 ........................................................................................................................ 83
第五章 結論與建議 ................................................................................................................ 85
5.1 結論 ............................................................................................................................... 85
5.2 建議 ............................................................................................................................... 86
參考文獻 ................................................................................................................................. 87
附錄 ......................................................................................................................................... 92
附錄一、各組別分類準確度評估 ...................................................................................... 92
附錄二、論文口試意見回覆表 ........................................................................................ 126
英文文獻
Anderson, J. E., Plourde, L. C., Martin, M. E., Braswell, B. H., Smith, M. L., Dubayah, R. O., Hofton, M. A. and Blair, J. B., 2008. “Integrating waveform lidar with hyperspectral imagery for inventory of a northern temperate forest,” Remote Sensing of Environment, Vol. 112 , pp. 1856-1870.

Beucher, S. and Lantuéjoul, C., 1979. “Use of watersheds in contour detection” in Proc. Int. Workshop Image Processing, Real-Time Edge and Motion Detection/Estimation, Rennes, France, pp.17-21.

Canty, M. J., 2010. Image analysis, classification, and change detection in remote sensing:with algorithms for ENVI/IDL, 2nd ed., CRC Press.

Carrão, H., Gonçalves, P. and Caetano, M., 2008. “Contribution of Multispectral and Multitemporal Information from MODIS Images to Land Cover Classification,” Remote Sens. Environ., Vol. 112, pp. 986-997.

Chen, C. M., Hepner, G. F. and Forster, R. R., 2003. “Fusion of Hyperspectral and Radar Data Using the HIS Transformation to Enhance Urban Surface Features,” ISPRS J. Photogramm., Vol. 58, pp. 19-30.

Cihlar, J., 2000. “Land cover mapping of large areas from satellites: status and research priorities,” Int. J. Remote Rensing, Vol. 21, No. 6 & 7, pp. 1093-1114.

Davies, E. R., 1991. “Median and mean filters produce similar shifts on curved boundaries,” Electronics Letters,Vol. 27, No. 10.

Davies, E. R., 1999, “Image distortions produced by mean, median and mode filters,” IEE Proceedings on Vision, Image and Signal Processing, Vol. 146, No. 5, pp. 279-285.

Duda, R. O., Hart, P. E. and Stork, D. G., 2001. “Pattern classification,” Wiley, New York.

Goetz, A. F. H., Vane, G., Solomon, J. E. and Rock, B. N., 1985. “Imaging spectrometry for Earth remote sensing, ” Science, 228, pp. 1147−1153.


Gonçalves, P., Carrão, H., Pinheiro, A. and Caetano, M., 2006. “Land Cover Classification with Support Vector Machine Applied to MODIS Imagery,” Global Developments in Environmental Earth Observation from Space, Rotterdam: Millpress, pp. 517-526.

Green, R. O., Eastwood, M. L., Sarture, C. M., Chrien, T. G., Aronsson, M., Chippendale, B. J., Faust, J. A., Pavri, B. E., Chovit, C. J., Solis, M., Olah, M. R. and Williams, O., 1998. “Imaging spectroscopy and the airborne visible/infrared imaging spectrometer (AVIRIS) ,” Remote Sensing of Environment, Vol. 65, No. 3, pp. 227−248.

Gustavo, C. V., Luis, G. C., Javier, C. M., Jose, David, M. G., Emilio, S. O., Luis, A. C., and Jose Moreno, 2004. “Robust Support Vector Method for Hyperspectral Data Classification and Knowledge Discovery,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 42, No. 7, pp. 1530−1542.

Huang, C., Davis, L. S. and Townshend, J. R. G., 2002. “An Assessment of Support Vector Machines for Land Cover Classification,” Int. J. Remote Sens., Vol. 23, pp. 725-749.

Huang, X. and Zhang, L., 2008. “An Adaptive Mean-Shift Analysis Approach for Object Extraction and Classification From Urban Hyperspectral Imagery, ” IEEE T. Geosci. Remote., Vol. 46, pp. 4173-4185

Itten, K. I., 2012. “THE EMERGENCE OF IMAGING SPECTROMETRY IN EUROPE,” Remote Sensing Laboratories, University of Zurich, 8057 Zurich, Switzerland.

Jung, C. R., 2007. “Combining Wavelets and Watersheds for Robust Multiscale Image Segmentation, ” Image Vision Comput, Vol. 25, pp. 24-33.

Landis, J. and Koch, G., 1977. “The Measurement of Observer Agreement for Categorical Data.Biometrics,” Vol. 33, pp.159-174.

Li, L., Ustin, S. L. and Lay, M., 2005. “Application of AVIRIS Data in Detection of Oil-Induced Vegetation Stress and Cover Change at Jornada,” Remote Sens. Environ., Vol. 94, New Mexico, pp. 1-16.

Li, P. and Xiao, X., 2004. “Evaluation of multiscale morphological segmentation of multispectral imagery for land cover classification,” Proceedings of IEEE Geoscience and Remote Sensing Symposium., IGARSS 04, pp. 2676-2679.

Lillesand, T. M. and Kiefer, R. W., 2000. Remote Sensing and Image Interpretation, 4^th Edition, New York.

Mahesh, P. and Mather, P. M., 2004. “Assessment of the effectiveness of support vector machines for hyperspectral data,” Future Generation Computer Systems, Vol. 20, No.7 , pp. 1215 -1225.

Meyer, F. and Beucher, S., 1990. “Morphological segmentation,” J. Vis. Commun. Image R., Vol. 1, pp. 21-46.

Muneyasu, M., Hotta, K. and Hinamoto, T., 1998. “Edge-preserving smoothing using median mean neural hybrid filters,” J. franklin inst, Vol. 335, No. 6, pp.1145-1156.

Navon, E., Miller, O. and Averbuch, A., 2005. “Color Image Segmentation Based on Adaptive Local Thresholds,” Image Vision Comput., Vol. 23, pp. 69-85.

Parker, J. R., 1997. Algorithms for Image Processing and Computer Vision, Wiley, New York.

Plaza, A., Benediktsson, J. A., Boardman, J. W., Brazile, J., Bruzzone, L., Camps-Valls,G., Chanussot, J., Fauvel, M., Gamba, P., Gualtieri, A., Marconcini, M., Tilton, J. C. and Trianni, G., 2009. “Recent Advances in Techniques for Hyperspectral Image Processing,” Remote Sens. Environ., Vol. 113, pp. S110−S122.

Plaza, A., Benediktsson, J. A., Boardman, J. W., Brazile, J., Bruzzone, L., Camps-Valls, G., Chanussot, J., Fauvel, M., Gamba, P., Gualtieri, A., Marconcini, M., Tilton, J. C. and Trianni, G., 2009. “Recent Advances in Techniques for Hyperspectral Image Processing,” Remote Sens. Environ., Vol. 113, pp. S110-S122.

Pratt, W. K., 2007. Digital Image Processing, 4th Edition., Wiley, New York.

Richards, J. A. and Jia, X. P., 1986. Remote Sensing Digital Image Analysis : An Introduction, 4th Edition.

Soille, P., 2003. Morphological Image Analysis, 2nd ed., Springer, Berlin.

Song, M. and Civco, D., 2004. “Road Extraction Using SVM and Image Segmentation,”Photogrammetric Engineering & Remote Sensing, Vol. 70, No. 12, pp. 1365-1371.
Surachat, K. and Amornraksa, T., 2009. “Pixel-wise based Digital Watermarking using Mean Filter in Chrominance channel,”International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS 2009) , pp.525-528.

Tarabalka, Y., Chanussot, J. and Benediktsson, J. A., 2010. “Segmentation and Classification of Hyperspectral Images Using Watershed Transformation,” Pattern Recogn, Vol. 43, pp. 2367-2379.

Vagni, F., 2007. “Survey of Hyperspectral and Multispectral Imaging Technologies,” The Research and Technology Organisation (RTO) of NATO.

Van der Linden, S., Janz, A., Eiden, M. and Hostert, P., 2007. “Classifying Segmented Hyperspectral Data from A Heterogeneous Urban Environment Using Support Vector Machines,” J. Appl. Remote Sens., Vol. 1, 013543.

Vapnik, V., 1998. Statistical Learning Theory, John Wiley, New York.

Watanachaturaporn, P., Arora, M. K. and Varshney, P. K., 2008. “Multisource Classification Using Support Vector Machines: An Empirical Comparison with Decision Tree and Neural Network Classifiers,”Photogrammetric Engineering & Remote Sensing, Vol. 74, No. 2, pp. 239-246.

Zenzo, S. D.,1986. “A note on the gradient of a multi-image,” Computer Vision, Graphics, and Image Processing, Vol. 33, No. 1, pp.116-125.

Zhang, L. and Huang, X., 2010. “Object-Oriented Subspace Analysis for Airborne Hyperspectral Remote Sensing Imagery,” Neurocomputing, Vol. 73, pp. 927-936.

Zhang, M., Qin, Z., Liu, X. and Ustin, S.L., 2003. “Detection of stress in tomatoes induced by late blight disease in California,” using hyperspectral remote sensing, Int. J. Appl. Earth Obs. 4, USA, pp. 295-310.


中文文獻
王俊芳、王正歡、王敏,2009,「常用圖像去噪濾波方法比較分析」,現代商貿工業期刊,第16期,第310-311頁。

李龍正,2004,「高光譜影像儀發展及影像市場前景」,科儀新知月刊,第二十六卷,第二期,第50-57頁。

李龍正,2007,「高光譜影像儀ISIS 及FUHSI」,科儀新知月刊,第二十九卷,第三期,第12-21頁。

胡蕾、張偉、覃慶炎,2007,「幾種圖像去噪算法的應用分析」,信息技術期刊,第7期,第81-83頁。

徐百輝,2007,「大地的辨識密碼-高光譜影像」,科學發展月刊,第416期,第13-19頁。

張宗貴、王潤生,2000,「基於譜學的成像光譜遙感技術發展與應用」,國土資源遙感,第3期,總第45期,第18-26頁。

郭麟霂,2000,「寒帶沼地高光譜影像分類之研究」,國立交通大學土木工程學系碩士論文,新竹。

陳建文,2006,「高光譜影像雜訊模式估計」,國立中央大學資訊工程研究所碩士論文,桃園。

蔡博文,2003,「子計畫一:台灣山地地區土地利用時序資料庫建立之研究(II)」,國立臺灣大學地理環境資源學系暨研究所成果報告,臺北。

鄧書斌,2010,ENVI遥感圖像處理方法,科學出版社。

繆紹綱譯,Gonzalez, R. C.,Woods, R. E. and Eddins, S. L.著,2006,「數位影像處理:運用MATLAB」,東華書局,台北。

魏子軒,2007,「高光譜影像分類辨識方法」,儀科中心簡訊,第84期,第14-15頁。

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top