Similar articles

Abstract: Classification of intertidal area in synthetic aperture radar (SAR) images is an important yet challenging issue when considering the complicatedly and dramatically changing features of tidal fluctuation. The difficulty of intertidal area classification is compounded because a high proportion of this area is frequently flooded by water, making statistical modeling methods with spatial contextual information often ineffective. Because polarimetric entropy and anisotropy play significant roles in characterizing intertidal areas, in this paper we propose a novel unsupervised contextual classification algorithm. The key point of the method is to combine the generalized extreme value (GEV) statistical model of the polarization features and the markov random field (MRF) for contextual smoothing. A goodness-of-fit test is added to determine the significance of the components of the statistical model. The final classification results are obtained by effectively combining the results of polarimetric entropy and anisotropy. Experimental results of the polarimetric data obtained by the Chinese Gaofen-3 SAR satellite demonstrate the feasibility and superiority of the proposed classification algorithm.

基于广义极值分布和马尔科夫随机场的全极化合成孔径雷达图像潮间带区域地物分类方法

[1]Akaike H, 1973. Information theory and an extension of the maximum likelihood principle. Proc 2^nd Int Symp on Information Theory, p.267-281.

[2]Boerner WM, 1990. Introduction to radar polarimetry—with assessments of the historical development and of the current state-of-the-art. In: Guran AS, Mittra R, Moser PJ (Eds.), Electromagnetic Wave Interactions. World Scientific, Singapore, p.139-214.

[3]Cloude SR, 1995. An entropy based classification scheme for polarimetric SAR data. Int Geoscience and Remote Sensing Symp, p.2000-2002.

[4]Cloude SR, Pottier E, 1996. A review of target decomposition theorems in radar polarimetry. IEEE Trans Geosci Remote Sens, 34(2):498-518.

[5]Ding H, Huang Y, Liu N, et al., 2015. Modeling of sea spike events with generalized extreme value distribution. European Radar Conf, p.113-116.

[6]Doulgeris AP, Akbari V, Eltoft T, 2012. Automatic PolSAR segmentation with the -distribution and Markov random fields. European Conf on Synthetic Aperture Radar, p.183-186.

[7]Geng XM, Li XM, Velotto D, et al., 2016. Study of the polarimetric characteristics of mud flats in an intertidal zone using C- and X-band spaceborne SAR data. Remote Sens Environ, 176:56-68.

[8]Inglada J, Garello R, 2000. Underwater bottom topography estimation from SAR images by regularization of the inverse imaging mechanism. Proc IEEE Int Geoscience and Remote Sensing Symp, p.1848-1850.

[9]Kim DJ, Park SE, Lee HS, et al., 2009. Investigation of multiple frequency polarimetric SAR signal backscattering from tidal flats. IEEE Int Geoscience and Remote Sensing Symp, p.896-899.

[10]Kim JE, Park SE, Kim DJ, et al., 2011. Recent advances in POL(in)SAR remote sensing and stress-change monitoring of wetlands with applications to the Sunchon Bay Tidal Flats. European Conf on Synthetic Aperture Radar, p.1-3.

[11]Lee H, Chae H, Cho SJ, 2011. Radar backscattering of intertidal mudflats observed by Radarsat-1 SAR images and ground-based scatterometer experiments. IEEE Trans Geosci Remote Sens, 49(5):1701-1711.

[12]Li HC, Hong W, Wu YR, 2007. Generalized gamma distribution with MoLC estimation for statistical modeling of SAR images. 1^st Asian and Pacific Conf on Synthetic Aperture Radar, p.525-528.

[13]Li SZ, 2009. Markov Random Field Modeling in Image Analysis. Springer, London, UK.

[14]Li Z, Heygester G, Notholt J, 2012. Topographic mapping of Wadden Sea, with SAR images and waterlevel model data. IEEE Int Geoscience and Remote Sensing Symp, p.2645-2648.

[15]Li Z, Heygester G, Notholt J, 2013. The topography comparsion between the year 1999 and 2006 of German tidal flat wadden sea analyzing SAR images with waterline method. IEEE Int Geoscience and Remote Sensing Symp, p.2443-2446.

[16]Li Z, Heygster G, Notholt J, 2014. Intertidal topographic maps and morphological changes in the German wadden sea between 1996–1999 and 2006–2009 from the waterline method and SAR images. IEEE J Sel Top Appl Earth Observ Remote Sens, 7(8):3210-3224.

[17]Park SE, Moon WM, Kim DJ, 2009. Estimation of surface roughness parameter in intertidal mudflat using airborne polarimetric SAR data. IEEE Trans Geosci Remote Sens, 47(4):1022-1031.

[18]Peli E, 1990. Contrast in complex images. J Opt Soc Am A, 7(10):2023-2040.

[19]Pottier E, 1998. Unsupervised classification scheme and topography derivation of POLSAR data on the H/A/a polarimetric decomposition theorem. Proc 4^th Int Workshop on Radar Polarimetry, p.535-548.

[20]She X, Qiu X, Lei B, et al., 2017. A classification method based on polarimetric entropy and GEV mixture model for intertidal area of PolSAR image. J Rad, 6(5):554-563 (in Chinese).

[21]Uebersax JS, 1982. A generalized Kappa coefficient. Educ Psychol Meas Sage Publ, 42(1):181-183.

[22]van del Wal D, Herman PMJ, van den Dool AW, 2005. Characterisation of surface roughness and sediment texture of intertidal flats using ERS SAR imagery. Remote Sens Environ, 98(1):96-109.

[23]Won ES, Ouchi K, Yang CS, 2013. Extraction of underwater laver cultivation nets by SAR polarimetric entropy. IEEE Geosci Remote Sens Lett, 10(2):231-235.

[24]Wu Y, Ji K, Yu W, et al., 2008. Region-based classification of polarimetric SAR images using Wishart MRF. IEEE Geosci Remote Sens Lett, 5(4):668-672.