Terkos Havzası Sulak Alanları ve Civarının Hyperion EO-1 Görüntüsü ile Sınıflandırılması

220 bantlı hiperspektral Hyperion EO-1 uydu görüntüsü kullanılarak gerçekleştirilen bu çalışma ile Terkos havzası sulak alanları ve civarının arazi örtüsü ve arazi kullanımı özelliklerinin yüksek doğrulukta ortaya konması için çeşitli analizler gerçekleştirilmiştir. Çalışma için üç farklı metodoloji izlenmiştir. Öncelikle Hyperion EO-1 göntüsünün ön işlemesi gerçekleştirilmiştir. İlk uygulama ön işlemesi yapılan görüntünün spektral dört bölgeye ayrılması ve her bir bölgenin en çok benzerlik kontrollü sınıflandırma yöntemi ile sınıflandırılmasını içermektedir. İkinci uygulamada dört spektral bölgenin herbirine Ana Bileşen Dönüşümü ABD uygulanmış ve oluşturulan sekiz bantlı yeni görüntü en çok benzerlik yöntemi ile sınıflandırılmıştır. Üçüncü analiz ise ön işleme yapılmış görüntüye ABD uygulanması ve ilk üç bileşenin kontrollü sınıflandırılmasını içermektedir. Genel doğruluk ve Kappa istatistikleri ile üç yöntemin doğruluk değerlendirmesi yapılmıştır.

Anahtar Kelimeler:

Uzaktan algılama, Görüntü İşleme, Sınıflandırma, Hyperion EO-1, Sulak Alan.

Classification of Terkos Basin Wetlands Environment Using Hyperion-EO-1 Image

In this study, different analyses were conducted to determine Terkos basin wetlands and surrounded land use and land cover with high accuracy by using Hyperion EO-1 data with 220 spectral bands. Three different methodologies were followed. Firstly, image preprocessing steps were applied to data. The first application included the segmentation of the pre-processed Hyperion data into four spectral regions and classification of each region using maximum likelihood supervised classification method. In the second application, Principal Component Analysis PCA was applied to each spectral region and eight different components were gathered from spectral regions. Supervised classification was applied to new data set. In the third analysis, PCA was implemented to pre-processed data and three components were selected for supervised classification. Overall accuracy and Kappa statistics were applied for the accuracy assessment of the three analyses.

Keywords:

Remote Sensing, Image Processing, Classification, Hyperion EO-1, Wetlands.,

PDF

___

Adam E, Mutanga O, Rugege D, 2010: Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: a review, Wetlands Ecology and Management, 18, 3, 281-296.
Adler Golden M. S, Matthew M. W, Bernstein, L. S, Levine, R. Y, Berk A, Richtsmeier S. C, Acharya P. K, Anderson G. P, Felde G, Gardner J, Hoke M, Jeong L. S, Pukall B, Mello A, Ratkowski A, Burke H. H, 1999: Atmospheric correction for shortwave spectral imagery based on MODTRAN4, SPIE Proceeding, Imaging Spectrometry V, 3753.
Bektaş Balçık F., 2010: Mapping and Monitoring Wetland Environment by Analysis of Different Satellite Images and Field Spectroscopy, Doktora Tezi, İTU Fen Bilimleri Enstitüsü, İstanbul.
Butera M. K, 1983: Remote Sensing of Wetlands. IEEE Transactions on Geoscience and Remote Sensing, 21, 3, 383–392.
Cudahy T. J, Hewson R.D, Huntington J.F, Quigley,M.A, ve Barry P.S, 2001: The performance of the satellite-borne Hyperion Hyperspectral VNIR-SWIR imaging system for mineral mapping at Mount Fitton, South Australia, Proceedings, IEEE 2001 International Conference on Geoscience and Remote Sensing.
Dechka J.A, Franklin S.E, Watmough M.D, Bennett R. P, Instrup, D.W, 2002: Classification Of Wetland Habitat and Vegetation Communities Using Multi-Temporal Ikonos Imagery In Southern Sakatchewan, Canadian Journal of Remote Sensing, 28, 5, 679-685.
Eastman, R.J, 2001: Guide to GIS and Image Processing Volume.2, Clarke Lab. Clark University Worcester, MA USA, 57-74.
Galvão L. S, Formaggio A. R, ve Tisot D. A, 2005: Discrimination of sugarcane varieties in Southeastern Brazil with EO-1 Hyperion data, Remote Sensing of Environment, 94, 4, 523- 534.
Goodenough D.G, Dyk A, Niemann K.O, Pealman J.S, Chen H, Han, T, Murdoch M, ve West C, 2003: Preprocessing Hyperion and ALI for forest classification, IEEE Transaction on Geoscience and Remote Sensing, 41, 6, 1321−1331.
Guerschman J. P, Hill M. J, Renzullo L. J, Barrett D. J, Marks A. S, ve Botha E. J, 2009: Estimating fractional cover of photosynthetic vegetation, non-photosynthetic vegetation and bare soil in the Australian tropical savanna region upscaling the EO-1 Hyperion and MODIS sensors, Remote Sensing of Environment, 113, 5, 928-945.
Jackson B. B, 1983: Multivariate Data Analysis: An Introduction, Irwin, Homewood, Illinois, USA.
Jensen J.R, Hodgson M.E, Christensen E. Mackey, H. E, Tinney L.R., ve Sharitz R, 1986: Remote sensing of Inland Wetlands: A Multispectral Approach, Photogrammetric Engineering and Remote Sensing, 52, 1, 87-100
Kindscher K, Fraser A, Jakubauskas M.E, ve Debinski D, 1998: Identifying Wetland Meadows in Grand Teton National Park Using Remote Sensing and Average Wetland Values, Wetlands Ecology and Management, 5, 265-273.
Kokaly R. F, Clark R. N, 1999: Spectroscopic determination of leaf biochemistry using band-depth analysis of absorption features and stepwise linear regression, Remote Sensing of Environment, 67, 267–287.
Mitsch W. J, ve Gosselink J. G, 2000: Wetlands, 3rd edition, John Wiley & Sons, Inc., New York.
Mumby P. J, ve Edwards A. J, 2002: Mapping Marine Environments With Ikonos Imagery: Enhanced Spatial Resolution Can Deliver Greater Thematic Accuracy, Remote sensing of Environment, 22, 12, 2377-2400.
Özeşmi S. L, ve Bauer M. E, 2002: Satellite Remote Sensing Of Wetlands, Wetlands Ecology and Management, 10, 381-402.
Özhatay N, Byfield. A, ve Atay, S, 2003: Türkiye’nin Önemli Bitki Alanları, WWF Turkiye, MAS Press (in Turkish).
Ramsar Convention Bureau, 2002: The Ramsar Convention on Wetlands, http://www.ramsar.org, 01.08.2010
Rundquist D. C, Narumalani S, Narayanan, R, M, 2001: A Review of Wetlands Remote Sensing and Defining New Considerations, Remote Sensing Reviews, International Journal of Remote Sensing, 20, 3, 207-226
Schmidt K. S, Skidmore A. K, 2003: Spectral discrimination of vegetation types in a coastal wetland, Remote Sensing of Environment, 85, 1, 92-108.
Yılmaz R, 2010: Monitoring land use/land cover changes using CORINE land cover data: a case study of Silivri coastal zone in Metropolitan Istanbul, Environmental Monitoring and Assessment, 165, 1-4, 603-615