Texture Analysis in SAR Imagery using the GI0 Distribution

GAMBINI, JULIANA; LUCINI, MARÍA MAGDALENA; CASETTI, JULIA; FRERY, AC

Maceio

Conferencia; XVIII Conference on Nonequilibrium Statistical Mechanics and Nonlinear Physics; 2014

UFAL, ITBA, Universidad de los Andes

In this paper we analyze a SAR imagery feature detection method when several strategies for estimation of the roughness parameter of the G0 I distribution are applied. It has been shown that this distribution is able to characterize a large number of targets in monopolarized SAR imagery, deserving the denomination of ?Universal Model?. It is indexed by three parameters: the number of looks (which can be estimated in the whole image), a scale parameter, and the roughness or texture parameter. The latter is closely related to the number of elementary backscatters in each pixel, one of the reasons for receiving attention in the literature. We analyze the results of applying a feature detector method when the texture parameter of the G0 I distribution is estimated using several algorithms for parameter estimation including Maximum Likelihood, those based on fractional moments [3], log-cumulants [1, 2, 5] and a new procedure recently presented in [4]. The latter method is based on estimate the underlying distribution using asymmetric kernels and stochastic distances. References [1] S.N. Anfinsen and T. Eltoft. Application of the matrix-variate Mellin transform to analysis of polarimetric radar images. IEEE Transactions on Geoscience and Remote Sensing, 49(6):2281? 2295, 2011. [2] F. Bujor, E. Trouve, L. Valet, J-M Nicolas, and J.-P. Rudant. Application of log-cumulants to the detection of spatiotemporal discontinuities in multitemporal SAR images. IEEE Transactions on Geoscience and Remote Sensing, 42(10):2073?2084, 2004. [3] A. C. Frery, H.-J. M¨uller, C. C. F. Yanasse, and S. J. S. Sant?Anna. A model for extremely heterogeneous clutter. IEEE Transactions on Geoscience and Remote Sensing, 35(3):648?659, 1997. [4] J. Gambini, J. Cassetti, M. Lucini, and A. Frery. Parameter estimation in SAR imagery using stochastic distances and asymmetric kernel. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8:In Press, 2014. [5] S. Khan and R. Guida. Application of Mellin-Kind statistics to polarimetric G distribution for SAR data. IEEE Transactions on Geoscience and Remote Sensing, 52(6):3513?3528, June 2014. 1