Astatistical distribution texton feature for synthetic aperture radar image classification

Abstract

We propose a novel statistical distribution texton (s-texton) feature for synthetic aperture radar (SAR) image classification. Motivated by the traditional texton feature, the framework of texture analysis, and the importance of statistical distribution in SAR images, the s-texton feature is developed based on the idea that parameter estimation of the statistical distribution can replace the filtering operation in the traditional texture analysis of SAR images. In the process of extracting the s-texton feature, several strategies are adopted, including pre-processing, spatial gridding, parameter estimation, texton clustering, and histogram

Keywords

Synthetic aperture radar / Statistical distribution / Parameter estimation / Image classification

References

[1] Benboudjema, D., Tupin, F., 2013. Markovian modelling and Fisher distribution for unsupervised classification of radar images. Int. J. Remote Sens., 34(22):8252–8266.

[2] Fukuda, S., 2004. Relating polarimetric SAR image texture to the scattering entropy. Proc. IEEE Int. Geoscience and Remote Sensing Symp., p.2475–2478.

[3] Gambini, J., Mejail, M.E., Jacobo-Berlles, J., , 2006. Feature extraction in speckled imagery using dynamic B-spline deformable contours under the G0 model. Int. J. Remote Sens., 27(22):5037–5059.

[4] He, C., Ahonen, T., Pietikainen, M., 2008. A Bayesian local binary pattern texture descriptor. Proc. 19th Int. Conf. on Pattern Recognition, p.1–4.

[5] He, C., Li, S., Liao, Z., , 2013. Texture classification of PolSAR data based on sparse coding of wavelet polarization textons. IEEE Trans. Geosci. Remote Sens., 51(8):4576–4590.

[6] Krylov, V., Moser, G., Serpico, S.B., , 2008. Modeling the Statistics of High Resolution SAR Images. Research Report RR-6722, INRIA, France.

[7] Krylov, V., Moser, G., Serpico, S.B., , 2009. Dictionarybased probability density function estimation for highresolution SAR data. Proc. IS&T/SPIE Electronic Imaging, p.72460S.1–72460S.12.

[8] Krylov, V.A., Moser, G., Serpico, S.B., , 2013. On the method of logarithmic cumulants for parametric probability density function estimation. IEEE Trans. Image Process., 22(10):3791–3806.

[9] Kuruoglu, E.E., Zerubia, J., 2000. Modelling SAR with a generalisation of the Rayleigh distribution. IEEE Trans. Image Process., 13(4):527–533.

[10] Kuruoglu, E.E., Zerubia, J., 2003. Skewed α-stable distributions for modelling textures. Patt. Recog. Lett., 24(1-3):339–348.

[11] Leung, T., Malik, J., 2001. Representing and recognizing the visual appearance of materials using three-dimensional textons. Int. J. Comput. Vis., 43(1):29–44.

[12] Oliver, C.J., 1986. A model for non-Rayleigh scattering statistics. Opt. Acta: Int. J. Opt., 31(6):701–722.

[13] Oliver, C.J., Quegan, S., 2004. Understanding Synthetic Aperture Radar Images. SciTech Publishing, Stevenage.

[14] Schmid, C., 2001. Constructing models for content-based image retrieval. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, p.39–45.

[15] Silveira, M., Heleno, S., 2009. Separation between water and land in SAR images using region-based level sets. IEEE Geosci. Remote Sens. Lett., 6(3):471–475.

[16] Singh, J., Datcu, M., 2013. SAR image categorization with log cumulants of the fractional Fourier transform coefficients. IEEE Trans. Geosci. Remote Sens., 51(12): 5273–5282.

[17] Spigai, M., Tison, C., Souyris, J.C., 2011. Time-frequency analysis in high-resolution SAR imagery. IEEE Trans. Geosci. Remote Sens., 49(7):2699–2711.

[18] Varma, M., Zisserman, A., 2002. Classifying images of materials: achieving viewpoint and illumination independence. Proc. European Conf. on Computer Vision, p.255–271.

[19] Varma, M., Zisserman, A., 2005. A statistical approach to texture classification from single images. Int. J. Comput. Vis., 62(1-2):61–81.

[20] Voisin, A., Moser, G., Krylov, V.A., , 2010. Classification of very high resolution SAR images of urban areas by dictionary-based mixture models, copulas and Markov random fields using textural features. Proc. SPIE Remote Sensing, p.585–599.

[21] Xie, X., 2008. A review of recent advances in surface defect detection using texture analysis techniques. Electron. Lett. Comput. Vis. Image Anal., 7(3):1–22.

[22] Yonezawa, C., Watanabe, M., Saito, G., 2012. Polarimetric decomposition analysis of ALOS PALSAR observation data before and after a landslide event. Remote Sens., 4(8):2314–2328.

RIGHTS & PERMISSIONS

Zhejiang University and Springer-Verlag GmbH Germany