Classification of Satellite Images Using Decision Trees:
Year 2010,
Volume: 2 Issue: 1, 36 - 45, 01.03.2010
Taşkın Kavzoğlu
İsmail Çölkesen
Abstract
Remotely sensed images have been primary data sources for many studies since they provide distinctive advantages. For the extraction of various geo-information from satellite images classification is the most widely used approach. The levels of accuracy and currency of the thematic maps produced through classification have direct impacts on the results. Many algorithms have been developed in the literature for this purpose. Decision trees with flowchart-like structures that have been recently employed in the classification of satellite images are supervised classification techniques successfully used in many fields. Their non-parametric nature and process speed in problem solving have made decision trees widely used and preferred methods. In this study, classification performance of the decision trees was thoroughly analysed using a recent Landsat ETM+ imagery. Performance of decision trees was compared with the maximum likelihood classifier that has been the most widely used classifier. Performances of the classifiers for the data set considered in this study were statistically evaluated using Z test. Results show that decision trees are effective in the classification of satellite images.
References
- Campbell, J.B., 1996, “Introduction to Remote Sensing”, Guilford Press, New York, 621 s.
- Townshend J.R.G., 1992, “Land cover”, International Journal of Remote Sensing, 13, 1319–1328
- Hall F.G., Townshend J.R.G., Engman E. T., 1995, “Status of remote sensing algorithms for estimation of land surface state parameters”, Remote Sensing of Environment, 51, 138–156
- Lu D., Weng Q., 2007, “A survey of image classification methods and techniques for improving classification performance”, International Journal of Remote Sensing, 28, 823–870
- Huang C., Davis L.S., Townshend, J.R.G., 2002, “An assessment of support vector machines for land cover classification”, International Journal of Remote Sensing, 23, 725–749
- Erbek, F.S., Özkan, C., Taberner, M., 2003, “Comparison of maximum likelihood classification method with supervised artificial neural network algorithms for land use activities”, International Journal of Remote Sensing, 25, 1733-1748
- Pal, M., Mather, P.M., 2005, “Support vector machines for classification in remote sensing”, International Journal of Remote Sensing, 26, 1007-1011
- Kavzoglu, T., Colkesen, I., 2009, “A kernel functions analysis for support vector machines for land cover classification”, International Journal of Applied Earth Observation and Geoinformation, 11, 352-359
- Paola, J.D., 1994, “Neural network classification of multispectral imagery”, MSc Thesis, The University of Arizona, USA
- Foody, G.M., 1995, “Using prior knowledge in artificial neural network classification with a minimal training set”, International Journal of Remote Sensing, 16, 301-312
- Pal M., Mather P.M., 2003, “An assessment of the effectiveness of decision tree methods for land cover classification”, Remote Sensing of Environment, 86, 554-565
- Foody, G.M., 2004, “Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy”, Photogrammetric Engineering and Remote Sensing, 70, 627-633
- Mather, P.M., 1987, “Computer Processing of Remote-Sensed Images”, John Wiley and Sons, 125 s
- Safavian S.R., Landgrebe D., 1991, “A survey of decision tree classifier methodology”, IEEE Transactions on Systems Man and Cybernetics, 21, 660-674
- Quinlan J.R., 1993, “C4.5: Programs for Machine Learning”, Morgan Kaufmann, San Mateo, CA, 302 s
- Friedl M.A., Brodley C.E., 1997, “Decision tree classification of land cover from remotely sensed data”, Remote Sensing of Environment, 61, 399–409
- DeFries R., Hansen M., Townshend J.R.G., Sohlberg R., 1998, “Global land cover classifications at 8 km spatial resolution: the use of training data derived from Landsat imagery in decision tree classifiers”, International Journal of Remote Sensing, 19, 3141–3168
- Swain P.H., Hauska H., 1977, “Decision tree classifier - design and potential”, IEEE Transactions on Geoscience and Remote Sensing, 15, 142-147
- Breiman L., Friedman J.H., Olshen R.A. and Stone C.J., 1984, “Classification and Regression Trees” Monterey, CA: Wadsworth, 358 s
- Mingers J., 1989, “An empirical comparison of pruning methods for decision tree induction”, Machine Learning, 4, 227–243
- Quinlan J.R., 1987, “Simplifying decision trees”, International Journal of Man-Machine Studies, 27, 221-234
- Özkan, Y., 2008, “Veri Madenciliği Yöntemleri”, Papatya Yayıncılık Eğitim, İstanbul, 216 s
Karar Ağaçları İle Uydu Görüntülerinin Sınıflandırılması:
Year 2010,
Volume: 2 Issue: 1, 36 - 45, 01.03.2010
Taşkın Kavzoğlu
İsmail Çölkesen
Abstract
Uzaktan algılanmış uydu görüntüleri sağladığı önemli avantajlar sayesinde birçok çalışma için öncelikli veri kaynağı olmuştur. Uydu görüntülerinden yeryüzüne ait çeşitli bilgilerin elde edilmesinde en çok başvurulan yöntem görüntülerin sınıflandırılmasıdır. Sınıflandırma sonucu elde edilen tematik haritaların doğruluk ve güncellik derecesi sonuçlar üzerinde doğrudan etkilidir. Bu amaca yönelik olarak günümüze kadar birçok sınıflandırma algoritması geliştirilmiştir. Uydu görüntülerin sınıflandırılmasında son yıllarda kullanılmaya başlayan karar ağaçları, akış şemalarına benzeyen yapılarıyla birçok alanda başarıyla kullanılan bir kontrollü sınıflandırma yöntemidir. Yöntemin parametrik olmayan yapısı ve problem çözümündeki hızı, kullanımını yaygın hale getirmiştir. Bu çalışmada, karar ağaçlarının sınıflandırma performansı güncel bir Landsat ETM+ uydu görüntüsü kullanılarak detaylı şekilde analiz edilmiştir. Yöntemin sınıflandırma performansı yaygın kullanıma sahip en çok benzerlik yönteminin performansı ile karşılaştırılmıştır. Çalışmada kullanılan veri seti için sınıflandırma yöntemlerinin performansları istatistiksel olarak Z testi ile analiz edilmiştir. Elde edilen sonuçlar karar ağaçlarının uydu görüntülerinin sınıflandırmasında etkin bir yöntem olduğunu göstermiştir.
References
- Campbell, J.B., 1996, “Introduction to Remote Sensing”, Guilford Press, New York, 621 s.
- Townshend J.R.G., 1992, “Land cover”, International Journal of Remote Sensing, 13, 1319–1328
- Hall F.G., Townshend J.R.G., Engman E. T., 1995, “Status of remote sensing algorithms for estimation of land surface state parameters”, Remote Sensing of Environment, 51, 138–156
- Lu D., Weng Q., 2007, “A survey of image classification methods and techniques for improving classification performance”, International Journal of Remote Sensing, 28, 823–870
- Huang C., Davis L.S., Townshend, J.R.G., 2002, “An assessment of support vector machines for land cover classification”, International Journal of Remote Sensing, 23, 725–749
- Erbek, F.S., Özkan, C., Taberner, M., 2003, “Comparison of maximum likelihood classification method with supervised artificial neural network algorithms for land use activities”, International Journal of Remote Sensing, 25, 1733-1748
- Pal, M., Mather, P.M., 2005, “Support vector machines for classification in remote sensing”, International Journal of Remote Sensing, 26, 1007-1011
- Kavzoglu, T., Colkesen, I., 2009, “A kernel functions analysis for support vector machines for land cover classification”, International Journal of Applied Earth Observation and Geoinformation, 11, 352-359
- Paola, J.D., 1994, “Neural network classification of multispectral imagery”, MSc Thesis, The University of Arizona, USA
- Foody, G.M., 1995, “Using prior knowledge in artificial neural network classification with a minimal training set”, International Journal of Remote Sensing, 16, 301-312
- Pal M., Mather P.M., 2003, “An assessment of the effectiveness of decision tree methods for land cover classification”, Remote Sensing of Environment, 86, 554-565
- Foody, G.M., 2004, “Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy”, Photogrammetric Engineering and Remote Sensing, 70, 627-633
- Mather, P.M., 1987, “Computer Processing of Remote-Sensed Images”, John Wiley and Sons, 125 s
- Safavian S.R., Landgrebe D., 1991, “A survey of decision tree classifier methodology”, IEEE Transactions on Systems Man and Cybernetics, 21, 660-674
- Quinlan J.R., 1993, “C4.5: Programs for Machine Learning”, Morgan Kaufmann, San Mateo, CA, 302 s
- Friedl M.A., Brodley C.E., 1997, “Decision tree classification of land cover from remotely sensed data”, Remote Sensing of Environment, 61, 399–409
- DeFries R., Hansen M., Townshend J.R.G., Sohlberg R., 1998, “Global land cover classifications at 8 km spatial resolution: the use of training data derived from Landsat imagery in decision tree classifiers”, International Journal of Remote Sensing, 19, 3141–3168
- Swain P.H., Hauska H., 1977, “Decision tree classifier - design and potential”, IEEE Transactions on Geoscience and Remote Sensing, 15, 142-147
- Breiman L., Friedman J.H., Olshen R.A. and Stone C.J., 1984, “Classification and Regression Trees” Monterey, CA: Wadsworth, 358 s
- Mingers J., 1989, “An empirical comparison of pruning methods for decision tree induction”, Machine Learning, 4, 227–243
- Quinlan J.R., 1987, “Simplifying decision trees”, International Journal of Man-Machine Studies, 27, 221-234
- Özkan, Y., 2008, “Veri Madenciliği Yöntemleri”, Papatya Yayıncılık Eğitim, İstanbul, 216 s