Kaynaştırılmış Görüntülerden Elde Edilen Doku Özellikleri ile DVM Sınıflandırma Performansının İyileştirilmesi

Yıl 2019, , 190 - 199, 01.12.2019

Volkan Yılmaz

https://doi.org/10.29128/geomatik.507613

Öz

Uzaktan algılanmış görüntülerden elde edilen doku bilgisi yardımıyla yüksek doğruluklu arazi örtüsü haritalarının üretilmesi mümkündür. Kaynaştırılmış bir görüntüdeki doku bilgisinin sınıflandırma işlemine entegre edilmesinin sınıflandırma işleminin doğruluğuna olumlu yönde katkı yapması muhtemeldir. Bu çalışmada Brovey, Multiplicative (MCV), PCA (Principal Component Analysis), Gram-Schmidt (GS), HPF (High-Pass Filtering), Wavelet, Ehlers ve HCS (Hyperspherical Colour Sharpening) kaynaştırma yöntemleri kullanılarak bir WorldView-2 ÇB görüntüsü ile bir WorldView-2 PAN görüntüsü kaynaştırılmıştır. Elde edilen kaynaştırılmış görüntüler Watershed bölütleme (WB) algoritması ile bölütlenmiştir. Elde edilen bölütlerden dört adet eşdizimlilik doku özelliği çıkartılmıştır. Çıkartılan bu doku özellikleri destek vektör makineleri (DVM) sınıflandırıcısına entegre edilerek görüntü üzerindeki sınıfların birbirinden ayrılabilirliğinin arttırılması irdelenmiştir. Deneysel sonuçlar bütün kaynaştırma yöntemlerinden elde edilen doku özelliklerinin sınıflandırma doğruluğunu belli bir oranda arttırdığını göstermektedir. Wavelet ve Ehlers kaynaştırma yöntemlerinden elde edilen doku özelliklerinin sınıflandırma doğruluğunu %20.4 ve %18.9 oranında arttırarak bu alanda en başarılı kaynaştırma yöntemleri oldukları tespit edilmiştir. 

Anahtar Kelimeler

görüntü kaynaştırma, doku özelliklerinin hesaplanması, görüntü sınıflandırma, destek vektör makineleri, görüntü bölütleme

Kaynakça

• Akar, Ö., ve Güngör, O. (2015). Integrating multiple texture methods and NDVI to the Random Forest classification algorithm to detect tea and hazelnut plantation areas in northeast Turkey. International Journal of Remote Sensing, 36 (2), 442-464.
• Amarsaikhan, D., ve Douglas, T. (2004). Data fusion and multisource image classification. International Journal of Remote Sensing, 25 (17), 3529-3539.
• Anys, H., Bannari, A., He, D.C., ve Morin, D. (1994). Texture analysis for the mapping of urban areas using airborne MEIS-II images. 1st International Airborne Remote Sensing Conference and Exhibition, 3, 231-245.
• Blum, R.S., ve Liu, Z. (2005). Multi-sensor image fusion and its applications. CRC press.
• Chavez, A., ve Kwarteng, P. (1989). Extracting spectral contrast in Landsat Thematic Mapper image data using selective principal component analysis. Photogrammetric Engineering & Remote Sensing, 55, 339-348.
• Colditz, R.R., Wehrmann, T., Bachmann, M., Steinnocher, K., Schmidt, M., Strunz, G., ve Dech, S. (2006). Influence of image fusion approaches on classification accuracy: a case study. International Journal of Remote Sensing, 27 (15), 3311-3335.
• Congalton, R.G., ve Green, K. (1999). Assessing the Accuracy of Remotely Sensed Data: Principles and Practices. Boca Raton, FL: Lewis.
• Crippen, R.E. (1989). A simple spatial filtering routine for the cosmetic removal of scanline noise from Landsat TM P-tape imagery. Photogrammetric Engineering & Remote Sensing, 327-331.
• Ehlers, M. (2004). Spectral characteristics preserving image fusion based on Fourier domain filtering. Remote Sensing for Environmental Monitoring, GIS Applications, and Geology IV, 5574, 1-14.
• Erdas Imagine Field Guide, Leica Geosystems.
• Gangkofner, U.G., Pradhan, P.S., ve Holcomb, D.W. (2007). Optimizing the high-pass filter addition technique for image fusion. Photogrammetric Engineering & Remote Sensing, 73 (9), 1107-1118.
• Gauch, J.M. (1999). Image segmentation and analysis via multiscale gradient watershed hierarchies. IEEE Transactions on Image Processing, 8 (1), 69-79.
• Gungor, O. (2008). Multi sensor multi resolution image fusion. PhD thesis, Purdue University.
• Hallada, W.A., ve Cox, S. (1983). Image sharpening for mixed spatial and spectral resolution satellite systems”. 17th International Symposium on Remote Sensing of Environment, Ann Arbor, MI, 1023-1032.
• Haralick, R.M., Shanmugam, K., ve Dinstein, I.H. (1973). Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, SMC-3 (6): 610-621.
• Harris Geospatial Solutions, online help, http://www.harrisgeospatial.com/docs/backgroundtexturemetrics.html#Data, Erişim Tarihi: 13 Aralık 2018).
• Hill, P.R., Canagarajah, C.N., ve Bull, D.R. (2002). Image Fusion Using Complex Wavelets. In BMVC, 1-10.
• Klonus, S., ve Ehlers, M. (2007). Image fusion using the Ehlers spectral characteristics preservation algorithm. GIScience & Remote Sensing, 44 (2), 93-116.
• Laben, C.A., ve Brower, B.V. (2000). Process for enhancing the spatial resolution of multispectral imagery using pansharpening. U.S. Patent No. 6,011,875, Washington, DC: U.S.
• Liu, Y., ve Zheng, Y.F. (2005). One-against-all multi-class SVM classification using reliability measures. Neural Networks, 2, 849-854.
• Lloyd, C.D., Berberoglu, S., Curran, P.J., ve Atkinson, P.M. (2004). A comparison of texture measures for the per-field classification of Mediterranean land cover. International Journal of Remote Sensing, 25 (19), 3943-3965.
• Melgani, F., ve Bruzzone, L. (2004). Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 42, 1778–1790.
• Otazu, X., González-Audícana, M., Fors, O., ve Núñez, J. (2005). Introduction of sensor spectral response into image fusion methods. Application to wavelet-based methods. IEEE Transactions on Geoscience and Remote Sensing, 43 (10), 2376-2385.
• Padwick, C., Deskevich, M., Pacifici, F., ve Smallwood, S. (2010). WorldView-2 pansharpening. ASPRS 2010 Annual Conference, San Diego, CA, USA, vol. 2630.
• Park, J.H., ve Kang, M.G. (2004). Spatially adaptive multiresolution multispectral image fusion. International Journal of Remote Sensing, 25 (23), 5491–5508.
• Parvati, K., Rao, P., ve Mariya Das, M. (2008). Image segmentation using gray-scale morphology and marker-controlled watershed transformation. Discrete Dynamics in Nature and Society.
• Pohl, C., ve van Genderen, J. (2016). Remote sensing image fusion: A practical guide. Crc Press.
• Pohl, C., ve van Genderen, J.L. (1998). Multisensor image fusion in remote sensing: concepts, methods and applications. International Journal of Remote Sensing, 19 (5), 823-854.
• Puissant, A., Hirsch, J., ve Weber, C. (2005). The utility of texture analysis to improve per‐pixel classification for high to very high spatial resolution imagery. International Journal of Remote Sensing, 26 (4), 733-745.
• Ranchin, T. ve Wald, L. (2000). Fusion of high spatial and spectral resolution images: The ARSIS concept and its implementation. Photogrammetric Engineering & Remote Sensing, 66, 49–61.
• Schowengerdt, R.A. (1980). Reconstruction of multispatial, multispectral image data using spatial frequency content. Photogrammetric Engineering & Remote Sensing, 46 (10), 1325-1334.
• Serifoglu Yilmaz, C., Tunc Gormuş, E., ve Gungor, O. (2017). Texture Based Classification of Hyperspectral Images with Support Vector Machines Classifier. International Symposium on GIS Applications in Geography & Geosciences (ISGGG), Çanakkale, Turkey.
• Shafarenko, L., Petrou, M., ve Kittler, J. (1997). Automatic watershed segmentation of randomly textured color images. IEEE Transactions on Image Processing, 6 (11), 1530-1544.
• Simone, G., Farina, A., Morabito, F.C., Serpico, S.B., ve Bruzzone, L. (2002). Image fusion techniques for remote sensing applications. Information Fusion, 3 (1), 3-15.
• Stathaki, T. (2011). Image fusion: algorithms and applications. Elsevier.
• Sun, W., Chen, B., ve Messinger, D. (2014). Nearest-neighbor diffusion-based pansharpening algorithm for spectral images. Optical Engineering, 53 (1).
• Tarabalka, Y., Chanussot, J., ve Benediktsson, J.A. (2010). Segmentation and classification of hyperspectral images using watershed transformation. Pattern Recognition, 43 (7), 2367-2379.
• Tso, A., ve Mather, P.M. (2009). Classification methods for remotely sensed data. 2nd ed. Boca Raton, FL: CRC Press, Taylor and Francis Group. ISBN: 978-1-4200-9072-7.
• Vapnik, V.N. (1995). The nature of statistical learning theory. New York, NY: SpringerVerlag.
• Wald, L. (2000). Quality of high resolution synthesized images: Is there a simple criterion? In Proceedings of the third conference "Fusion of Earth data: merging point measurements, raster maps and remotely sensed images, Sophia Antipolis, France, 99-103.
• Wald, L. (2002). Fusion of Images of Different Spatial Resolutions. Presses de l'Ecole, Ecole des Mines de Paris, Paris, France, ISBN: 2-911762-38-X, 200 pp.
• Wald, L., Ranchin, T., ve Mangolini, M. (1997). Fusion of satellite images of different spatial resolutions: Assessing the quality of resulting images. Photogrammetric Engineering and Remote Sensing, 63, 691–699.
• Wang, Z., ve Bovik, A.C. (2002). A universal image quality index. IEEE Signal Processing Letters, 9 (3), 81-84.
• Wenbo, W., Jing, Y., ve Tingjun, K. (2008). Study of remote sensing image fusion and its application in image classification. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 37 (B7), 1141-1146.
• Yilmaz, V., Konakoglu, B., Serifoglu, C., Gungor, O., ve Gökalp, E. (2018). Image classification-based ground filtering of point clouds extracted from UAV-based aerial photos. Geocarto International, 33 (3), 310-320.
• Yilmaz, V., ve Gungor, O. (2016a). Determining the optimum image fusion method for better interpretation of the surface of the Earth. Norsk Geografisk Tidsskrift-Norwegian Journal of Geography, 70 (2), 69-81.
• Yilmaz, V., ve Gungor, O. (2016b). Fusion of very high-resolution UAV images with criteriabased image fusion algorithm. Arabian Journal of Geosciences, 9 (1).