volume | PIER Journals

Abstract

The near-field scattering characteristics of rough target are analyzed by using a revised bidirectional reflectance distribution function (BRDF) of a rough surface based on least squares support vector machine (LS-SVM). The revised BRDF is more reliable in a larger range of incident angles and scattering angles that beyond the scope of experimental measurements. The basic principle of LS-SVM and the modeling process are firstly introduced in detail. Then the comparison among LS-SVM, the back propagation neural network (BPNN) and the measured data is carried out．The results show that the LS-SVM model has better integrative performance, stronger generalization ability and higher precision. On this basis, the calculation of the near-field radar cross section (RCS) of a complex target is safely performed and analyzed. The method proposed is helpful to better investigate the near-field scattering characteristics of rough target.

1. Gibbs, D. P., C. L. Betty, A. K. Fung, and A. J. Blanchard, "Automated measurement of polarized bidirectional reflectance," Remote Sensing of Environment, Vol. 43, 97-114, 1993.
doi:10.1016/0034-4257(93)90067-8 Google Scholar

2. Li, H. K., N. Pinel, and C. Bourlier, "A monostatic illumination function with surface reflections from one-dimensional rough surfaces," Waves in Random and Complex Media, Vol. 21, 105-134, 2011.
doi:10.1080/17455030.2010.524263 Google Scholar

3. Ulaby, F. T., R. K. Moore, and A. K. Fung, Microwave Remote Sensing, Addison-Wesley, New York, 1982.

4. Arai, K., "Method for estimation of grow index of tealeaves based on Bi-directional reflectance distribution function: BRDF measurements with ground based network cameras," International Journal of Applied Sciences, Vol. 2, 52-62, 2011. Google Scholar

5. Jordan, D. L., "Experimental measurements of optical backscattering from surfaces of roughness comparable to the wavelength and their application to radar sea scattering," Waves in Random and Complex Media, Vol. 5, 41-54, 1995.
doi:10.1088/0959-7174/5/1/006 Google Scholar

6. Cook, R. L. and K. E. Torrance, "A reflectance model for computer graphics," Computer Graphics, Vol. 15, 307-316, 1981.
doi:10.1145/965161.806819 Google Scholar

7. Phong, B. T., "Illumination for computer generated pictures," Communications of the ACM, Vol. 18, 311-317, 1975.
doi:10.1145/360825.360839 Google Scholar

8. Ward, G. J., "Measuring and modeling anisotropic reflection," Computer Graphics, Vol. 26, 265-272, 1992.
doi:10.1145/142920.134078 Google Scholar

9. Oren, M. and S. K. Nayar, "Generalization of the Lambertian model and implications for machine vision," International Journal Computer Vision, Vol. 14, 227-251, 1995.
doi:10.1007/BF01679684 Google Scholar

10. Li, W., J. F. Chen, and T. Wang, "Prediction of the plasma distribution using an artificial neural network," Chinese Physics B, Vol. 18, 2441-2444, 2009.
doi:10.1088/1674-1056/18/6/053 Google Scholar

11. Vapnik, V., E. Levin, and Y. Le Cun, "Meaning the VC-dimension of a learning machine," Neural Computation, Vol. 6, 851-876, 1994.
doi:10.1162/neco.1994.6.5.851 Google Scholar

12. Balabin, R. M. and E. I. Lomakina, "Support vector machine regression (SVR/LS-SVM)-an alternative to neural networks (ANN) for analytical chemistry? Comparison of nonlinear methods on near infrared," Analyst, Vol. 136, 1703-1712, 2011.
doi:10.1039/c0an00387e Google Scholar

13. Wang, H. F. and D. J. Hu, "Comparison of SVM and LS-SVM for regression," International Conference on Neural Networks and Brain, Vol. 1, 279-283, 2005. Google Scholar

14. Suykens, J. A. K. and J. Vandewaiie, "Least squares support vector machine classifiers," Neural Processing Letter, Vol. 9, 293-300, 1999.
doi:10.1023/A:1018628609742 Google Scholar

15. Suykens, J. A. K., T. V. Gestel, J. D. Brabanter, B. D. Moor, and J. Vandewalle, Least Squares Support Vector Machines, World Scientific Publishers, Singapore, 2002.

16. Adankon, M. M., M. Cheriet, and A. Biem, "Semisupervised learning using Bayesian interpretation: Application to LS-SVM," IEEE Transactions on Neural Networks, Vol. 22, 513-524, 2011.
doi:10.1109/TNN.2011.2105888 Google Scholar

17. Gestel, V., et al. "Financial time series prediction using least squares support vector machines within the evidence framework," IEEE Transactions on Neural Networks, Vol. 12, 809-821, 2001.
doi:10.1109/72.935093 Google Scholar

18. Scholkopf, B. and S. Mika, "Input space vs. feature space in Kernel based methods," IEEE Trans. on Neural Networks, Vol. 10, 1000-1017, 1999.
doi:10.1109/72.788641 Google Scholar

19. Fletcher, R., Practical Methods of Optimization, John Wiley and Sons, Chichester and New York, 1987.

20. Browne, M. W., "Cross-validation methods," Journal of Mathematical Psychology, Vol. 44, 108-132, 2000.
doi:10.1006/jmps.1999.1279 Google Scholar

21. Guo, H., H. P. Liu, and L. Wang, "Method for selecting parameters of least squares support vector machines and application," Journal of System Simulation, Vol. 18, 2033-2036, 2006. Google Scholar

22. Hecht-Nielsen, R., "Theory of the backpropagation neural network," International Joint Conference on IEEE, 93-605, 1989. Google Scholar

23. Tomiyasu, K., "Relationship between and measurement of differential scattering coefficient and bidirectional reflectance distribution function (BRDF)," IEEE Transactions on Geoscience and Remote Sensing, Vol. 26, 660-665, 1988.
doi:10.1109/36.7692 Google Scholar

24. Andrews, L. C., M. A. Al-Habash, C. Y. Hopen, and R. L. Phillips, "Theory of optical scintillation: Gaussian-beam wave model," Waves in Random and Complex Media, Vol. 11, 271-291, 2001. Google Scholar

Dr. Ning Li

Prof. Min Zhang

Prof. Ding Nie

Dr. Wang-Qiang Jiang