|
||||||||||||||||
|
||||||||||||||||
|
||||||||||||||||
PIERS Online
Vol. 3
No. 5
2007
pp: 620-624A Hybrid Entropy Decomposition and Support Vector Machine Method for Agriculture Crop Type ClassificationChue-Poh Tan, Hong Tat Ewe, and Hean Teik Chuah doi:10.2529/PIERS060907095110 Downloads: 1288 Abstract:This paper presents the development of Synthetic Aperture Radar (SAR) image classifier based on the hybrid method of ``Entropy Decomposition and Support Vector Machine" (EDSVM) for agricultural crop type classification. The Support Vector Machine (SVM) is successfully applied to the key parameters extracted from Entropy Decomposition to obtain good image classifications. In this paper, this novel classifier has been applied on a multi-crop region of Flevoland, Netherlands with multi-polarization data for crop type classification. Validation of the classifiers has been carried out by comparing the classified image obtained from EDSVM classifier and SVM. The EDSVM classifier demonstrates the advantages of the valuable decomposed parameters and statistical machine learning theory in performing better results compared with the SVM classifier. The final outcome of this research clearly indicates that EDSVM has the ability in improving the classification accuracy for agricultural crop type classification.References:1. Ulaby, F. T., R. K. Moore, and A. K. Fung, Microwave Remote Sensing: Active and Passive, Artech House, Norwood, MA, 1986. 2. Bouman, B. A. M. and D. H. Hoekman, "Multi-temporal multi-frequency radar measurements of agricultural crops during the agriscatt-88 campaign in the netherlands," Int. J. Remote Sens., Vol. 14, 1595-1614, 1993. 3. Tran, T. N., R. Wehrens, D. H. Hoekman, and L. M. C. Buydens, "Initialization of markov random field clustering of large remote sensing images," IEEE Trans. Geosci. RemoteSensing, Vol. 43, No. 8, 1912-1919, 2005. 4. Van Zyl, J. J., "Unsupervised classification of scattering behavior using radar polarimetry data," IEEE Trans. Geosci. Remote Sensing, Vol. 27, No. 1, 36-45, Jan., 1989. 5. Cloude, S. R. and E. Pottier, "An entropy based classification scheme for land applications of polarimetric SAR," IEEE Trans. Geosci. Remote Sensing, Vol. 35, No. 1, 68-78, Jan., 1997. 6. Yahia, M. and Z. Belhadj, "Unsupervised classification of polarimetric sar images using neural networks," IEEE International Conference Information and Communication Technologies 2004, 335-337, 2004. 7. Lee, J. S., M. R. Grunes, and R. Kwok, "Classification of multi-look polarimetric SAR imagery based on complex wishart distribution," Int. J. Remote Sensing, Vol. 15, No. 11, 2299-2311, 1994. 8. Cloude, S. R. and E. Pottier, "A review of target decomposition theorems in radar polarimetry," IEEE Trans. Geoscience. Remote Sensing, Vol. 34, No. 2, 498-518, 1996. 9. Lee, J. S., M. R. Grunes, and T. L. Ainsworth, "Unsupervised classification using polarimetric decomposition and the complex wishart distribution," IEEE Transactions Geoscience. and Remote Sensing, Vol. 37, No. 5, 2249-2259, 1999. 10. Vapnik, V., The Nature of Statistical Learning Theory, Springer Verlag, 1999. 11. Schokopf, B. and A. J. Smola, Learning With Kernels, The MIT Press, Cambridge, Massachusetts, London, England, 2002. 12. Pottier, E., J. S. Lee, and L. Ferro-Famil, "Advanced concepts in polarimetric sar image analysis: a tutorial review," EuSAR 2006 Tutorial, EuSAR 2006 Conference, Dresden, Germany, May, 2006. |
||||||||||||||||
| © Copyright 2008 PIERS. All Rights Reserved. | ||||||||||||||||
