Aslı OK ÖZDARICI, Zuhal AKYÜREK

Çok tarihli optik ve mikrodalga görüntüleri kullanılarak tarım alanlarında yetiştirilen ürünlerin bölüt tabanlı sınıflandırılması üzerine bir yaklaşım

Çalışmada, Bursanın Karacabey ovasında yetiştirilen başlıca tarım ürünleri, çok tarihli Kompsat-2 ve Envisat ASAR görüntüleri ile otomatik olarak sınıflandırılmıştır. İlk olarak, tek tarihli pankromatik ve renkli Kompsat-2 görüntüleri uygun bir yöntem kullanılarak keskinleştirilmiş ve 1m mekânsal çözünürlüğe sahip renkli görüntüler elde edilmiştir. Bu görüntüler üzerinde daha sonra Ortalama Kaydırma yöntemi kullanılarak bölütleme işlemi uygulanmıştır. En uygun bölütleme sonucunu belirleyebilmek için her bir keskinleştirilmiş görüntü üzerinde mekân ve renk uzayında farklı parametre kombinasyonları denenmiştir. Elde edilen bölütler çeşitli istatistiksel yöntemler kullanılarak değerlendirilmiştir. Çalışmada piksel tabanlı ve bölüt tabanlı olmak üzere iki farklı sınıflandırma yaklaşımı test edilmiştir. Sınıflandırmalar ilk olarak tek tarihli renkli Kompsat-2 görüntüleri (4m) üzerinde uygulanmıştır. İkinci aşamada renkli Kompsat-2 görüntüleri, geri saçılım katsayıları hesaplanmış Envisat ASAR verileri ile birlikte sınıflandırılarak mikrodalga verilerinin görüntü sınıflamadaki katkısı incelenmiştir. Çok tarihli görüntülerin sınıflandırılması yoluyla elde edilen tematik haritalara ait bilgilerin birleştirilebilmesi amacıyla her bir tematik harita için uzaklık haritaları üretilmiştir. Bu yöntemle elde edilen piksel ve bölüt tabanlı haritalar, hata matrisleri yardımıyla değerlendirilmiştir. Sonuçlar, kullanılan Envisat ASAR verisinin sınıflandırma doğruluğunu arttırdığını göstermiştir. Hesaplamalar, en yüksek genel doğruluğun %88.71 ve 0.86 kappa değeri ile farklı tarihlerde çekilmiş Haziran-Ağustos ve Haziran-Temmuz-Ağustos aylarına ait görüntülerin birleşimi yoluyla elde edilen bölüt tabanlı sınıflandırma yaklaşımı için hesaplandığını ortaya koymuştur.

A segment-based approach to classify crop types in agricultural lands by using multi-temporal optical and microwave images

An automatic classification approach is performed to classify major crop types cultivated in Karacabey Plain, Bursa, through multi-temporal Kompsat-2 and Envisat ASAR data. First, the single-date pancromatic and multispectral Kompsat-2 images are fused with an appropriate image fusion method and 1m colour Kompsat-2 images are generated. Next, different parameter combinations are applied on the fused images in spatial and colour space to find out the optimum segmentation results. The optimum segments are then evaluated using multiple evaluation criteria. Two different classification approaches, pixel-based and segment-based, are tested in this study. First, Image classification are performed on the multispectral Kompsat-2 images. Then the Kompsat-2 images (4m) are classified with Envisat ASAR data. In this way contribution of the Envisat ASAR images to the classification accuracy are tested. Next, distance maps are produced for each thematic map to combine the information of multi-temporal images.The produced thematic maps are evaluated based on pixelbased and segment-based manner using confusion matrices. Results indicate that Envisat ASAR data improve the accuracy of thematic maps. The highest accuracies are obtained for the combined thematic maps of JuneAugust and June-July-August (%88.71 overall accuracy and 0.86 kappa) computed for the segment-based approach.

PDF

___

[1] Gong, P. and Howarth, P.J., (1990) The Use of Structural Information For Improving Land-Cover Classification Accuracies at the Rural-Urban Fringe, Photogrammetric Engineering and Remote Sensing, Vol. 56, pp. 67-73.
[2] Smith, G. M. and Fuller, R. M., (2001) An Integrated Approach to Land Cover Classification: An Example in the Island of Jersey, International Journal of Remote Sensing, Vol. 22, pp. 3123-3142.
[3] De wit, A. J. W. and Clevers, J. G. P. W, (2004), Efficiency and Accuracy of Per-Field Classification for Operational Crop Mapping, International Journal of Remote Sensing, Vol. 25, pp. 4091-4112.
[4] Gong, P., Marceau, D., and Howarth, P. J., (1992), A Comparison of Spatial Feature Extraction Algorithms for Land-Use Mapping With SPOT HRV data, Remote Sensing of Environment, Vol. 40, pp. 137-151.
[5] Gong, P. and Howarth, P. J, (1992), Frequency-Based Contextual Classification and Grey-Level Vector Reduction for Land Use Identification, Photogrammetric Engineering and Remote Sensing, Vol.58, pp.423-437.
[6] Yu, Q., Gong, P., Clinton N, Biging G, and Schirokauer D, (2006), Object-Based Detailed Vegetation Mapping Using High Spatial Resolution Imagery, Photogrammetric Engineering and Remote Sensing, Vol.72, pp.799-811.
[7] Schoenmakers, R. P. H. M.; Van Leeuwen H. J. C.; Lemoine, G. G., Nezry, E., 1994, Segmentation Of Combined High Resolution Optical and Radar Imagery for the Determination of Field Inhomogenities, Proceeding of IEEE, pp. 2137-2139.
[8] Cheng, Y, (1995), Mean Shift, Mode Seeking, and Clustering, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 17, pp. 790- 799.
[9] Rydberg, A. and Borgefors, G., (2001), Integrated Method for Boundary Delineation of Agricultural Fields in Multispectral Satellite Images, IEEE Transactions on Geoscience and Remote Sensing, Vol. 39, pp. 2514-2520.
[10] Mueller, M, Segl, K., and Kaufmann, H., (2003), Extracting Characteristic Segments in High- Resolution Panchromatic Imagery as Basic Information for Objects-Driven Image Analysis, Can. J. Remote Sensing, Vol. 29, pp. 453-457.
[11] Zhan, Q., Molenaar, M, Tempfli, K, and Shi, W. (2005), Quality Assessment for Geo-Spatial Objects Derived from Remotely Sensed Data. International Journal of Remote Sensing, Vol. 26, pp. 2953-2974.
[12] Chen, Z., Zhao, Z., Gong, P., and Zeng, B., (2006), A New Process for the Segmentation of High Resolution Remote Sensing Imagery, International Journal of Remote Sensing, Vol. 27, pp. 4991-5001.
[13] Lee, J. Y. and Warner, T. A., (2006), Segment Based Image Classification, International Journal of Remote Sensing, Vol. 27, pp. 3403-3412.
[14] Li, P. and X. Xiao, (2007), Multispectral Image Segmentation by a Multichannel Watershed- Based Approach, International Journal of Remote Sensing, Vol. 28, pp. 4429-4452.
[15] Lu, D. and Q. Weng (2007), A Survey of Image Classification Methods and Techniques For Improving Classification Performance, International Journal of Remote Sensing, Vol. 28, pp. 823-870.
[16] Corcoran, P., Winstanley, A., Mooney, P., (2010), Segmentation Performance Evaluation for Object-Based Remotely Sensed Image Analysis, International Journal of Remote Sensing, Vol. 31, pp. 617-645.
[17] Wang, D., Lin, H, Chen, J, Zhang, Y, Zeng, Q., (2010), Application of Multi-Temporal ENVISAT ASAR Data to Agricultural Area Mapping İn the Pearl River Delta, International Journal of Remote Sensing, Vol. 31, pp. 1555-1572.
[18] Xiao, P., Feng, X., An, R., and Zhao, S. (2010), Segmentation of Multispectral High-Resolution Satellite Imagery Using Log Gabor Filters, International Journal of Remote Sensing, Vol. 31, pp. 1427-1439.
[19] Liu, J. and Yang, Y-H., (1994), Multi- Resolution Color Image Segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 16, pp. 689-700.
[20] Zhang, Y. J, (1996), A Survey on Evaluation Methods for Image Segmentation, Pattern Recognition, Vol. 29, pp. 1335-1346.
[21] Zhang, Y. J., (2001), A Review of Recent Evaluation Methods for Image Segmentation, International Symposium on Signal Processing and its Applications (ISSPA), 13-16 August, Kuala Lumpur, Malaysia.
[22] Martin, D., Fowlkes, C., Tal, D., Malik, J., (2004), Learning to Detect Natural Image Boundaries Using Local Brightness, Color and Texture, IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 26, pp. 530-549.
[23] Chabrier, S., Emile, B., Rosenberg, C., and Laurent, H., (2006), Unsupervised Performance Evaluation of Image Segmentation, EURASIP Journal on Applied Signal Processing, Article Id: 96306, pp. 1-12.
[24] Ge, F., Wang, S., and Liu, T., (2006), Image- Segmentation Evaluation from the Perspective of Salient Object Extraction, Proceedings of the Computer Society Conference on Computer Vision and Pattern Recognition (CVPR06).
[25] Weidner, U., (2008), Contribution to the Assessment Of Segmentation Quality for Remote Sensing Applications, Proceedings of the 21st Congress for the International Society for Photogrammetry and Remote Sensing, 0311 July, Beijing, China.
[26] Parmuchi, M. G., Karszenbaum, H., and Kandus, P., (2002), Mapping Wetlands Using Multi- Temporal RADARSAT-1 Data and a Decision-Based Classifier, Can. J. Remote Sensing, Vol. 28, pp. 175- 186.
[27] Ban, Y., (2003), Synergy of Multitemporal ERS-1 SAR and Landsat TM Data for Classification of Agricultural Crops, Can. J. of Remote Sensing, Vol. 29, pp. 518-526.
[28] Blaes, X., Vanhalle, L., and Defourny, P., (2005), Efficiency of Crop Identification Based on Optical and SAR Image Time Series, Remote Sensing of Environment, Vol. 96, pp. 352-365.
[29] Türker, M. and Arıkan, M., (2005), Sequential Masking Classification of Multi-Temporal Landsat7 ETM+ Images for Field-Based Crop Mapping in Karacabey, Turkey, International Journal of Remote Sensing, Vol. 26, pp. 38133830.
[30] Liu, L., Wang, J., Bao, Y., Huang, W., Ma, Z., and Zhao, C., (2006), Envisat- Predicting Winter Wheat Condition, Grain Yield and Protein Content Using Multi-Temporal ASAR and Landsat TM Satellite Images, International Journal of Remote Sensing, Vol.27, pp.737-753.
[31] Stankiewicz, K. A., (2006), The Efficiency of Crop Recognition on Envısat Asar Images in Two Growing Season, IEEE Transactions on Geoscience and Remote Sensing, Vol. 44, pp. 806-814.
[32] Wang, D., H., Lin, J., Chen, Y., Zhang, Q. Zeng, (2010), Application of Multi-Temporal Envısat Asar Data to Agricultural Area Mapping in The Pearl River Delta, International Journal of Remote Sensing, Vol. 31, pp. 1555-1572.
[33] Penã-Barragán, M. J., Ngugi, M. K., Plant, R. E., and Six, J., (2011), Object-Based Crop Identification Using Multiple Vegetation Indices, Textural Features and Crop Phenology, Remote Sensing of Environment, Vol. 115, pp. 1301-1316.
[34] Skriver, H., Mattia, F., Satalino, G., Balenzano, A., Pauwels, V. R. N., Verhoest, N. E. C., and Davidson, M., (2011), Crop Classification Using Short-Revisit Multitemporal SAR Data, IEEE Journal of Selected Topics in Applied Earth Remote Sensing, Vol. 4, pp. 423-431.
[35] Nik System, (2008), Kompsat-2 technical notes. http://nik.com.tr/2008/tr/sistem/uydu_goruntuleri/kom psat2.html.
[36] Asar Ürün Kataloğu, (2009), Available Online at:http://envisat.esa.int/handbooks/asar (15.11.2009).
[37] PCI Geomatica, (2009), Geomatica OrthoEngine Course Guide. (Richmond Hill, ON: PCI Geomatics Enterprises Inc).
[38] Cheng, H. D., Jiang, X. H., Sun, Y., and Wang, J., (2001), Color Image Segmentation: Advances and Prospects, The Journal of the Pattern Recognition, Vol. 34, pp. 2259-2281.
[39] Comaniciu, D., Meer, P., (2002), Mean Shift: a Robust Approach Toward Feature Space Analysis, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, pp. 603-619.
[40] Clinton, N., Holt, A., Scarborough, J., Yan, L. I. and Gong, P., (2010), Accuracy Assessment Measures for Object-Based Image Segmentation Goodness, Photogrammetric Engineering and Remote Sensing, Vol. 76, pp. 289299.
[41] Lillesand, M., Kiefer, R. W., Chipman J W, (2004), Fifth Edition, Remote Sensing and Image Interpretation, (USA: John Wiley and Sons, Inc.), 638.
[42] Lillesand, T. M., Kiefer, R. W., (2000). Remote Sensing and Image Interpretation, New York: John Wiley and Sons.
[43] Türker, M. and Özdarıcı, A., (2011), Field- Based Crop Classification Using SPOT4, SPOT5, IKONOS, and Quickbird Imagery for Agricultural Areas: A Comparison Study, International Journal of Remote Sensing, Vol. 32, pp. 97359768.
[44] Chen, D. and Stow, D., (2002), The Effect of Training Strategies on Supervised Classification at Different Spatial Resolutions, Photogrammetric Engineering and Remote Sensing, Vol. 68, pp. 1155- 1161.
[45] Jensen, J. R., (2005), Introductory Digital Image Processing, Third Edition, USA: Pearson, Prentice Hall.
[46] Pouncey, R. and Swanson, K., (1999), ERDAS Manual, Fifth Ed., (USA: ERDAS), 540.