基于小波变换和马尔可夫随机场的极化SAR图像自动分类

刘国庆; 熊红; 黄顺吉

基于小波变换和马尔可夫随机场的极化SAR图像自动分类

计量
- 文章访问数: 2505
- HTML全文浏览量: 88
- PDF下载量: 433
- 被引次数: 0
出版历程
- 收稿日期: 1998-10-16
- 修回日期: 1999-05-22
- 刊出日期: 2000-05-19

AUTOMATIC MULTIRESOLUTION CLASSIFICATION OF POLARIMETRIC SAR IMAGE WITH WAVELET TRANSFORM AND MARKOV RANDOM FIELD

摘要

摘要: 本文提出一种对极化合成孔径雷达(SAR)图像进行自动多分辨率分类的方法。首先利用多视极化白化滤波(MPWF)抑制极化SAR图像的相干斑,得到反映地物辐射特征的纹理SAR图像,然后利用小波变换(WT)提取不同分辨率的纹理信息,在最低分辨率级利用Akaik信息准则(AIC)自动估计图像中的纹理类数,进而在各个分辨率级利用马尔可夫随机场(MRF)模型表征各像素间的空间关联信息,并分别利用最大似然(ML)方法和循环条件模式(ICM)进行自动的模型参数估计和最大后验概率(MAP)分类,最后应用NASA/JPL机载L波段极化SAR数据验证了本文所提分类方法的有效性和优越性。
- 极化合成孔径雷达（SAR）; 多分辨率; 分类; 小波变换（WT）; 马尔可夫随机场（MRF）; 最大后验概率（MAP）
Abstract: In this paper an automatic multiresolution classification method is proposed to classify polarimetric synthetic aperture radar (SAR) image.At first a textured SAR image characterizing the terrain reflection is obtained by using a multi-look polarimetric whitening filter (MPWF) to reduce the speckle in the polarimetric SAR image. Then the wavelet transform (WT) is utilized to extract texture information in different resolutions, and in the lowest resolution level the Akaik information criterion (AIC) is used for estimating the optimal number of texture classes in the image. Next the Markov random field (MRF) model is employed to characterize the spatial constraints between pixels in each resolution level, and a maximum like- lihood (ML) approach and an iterated conditional mode (ICM) approach are used for the model parameters estimation and maximum a posteriori (MAP) classification, respectively. Finally the paper presents the experimental results with the NASA/JPL L-band airborne polarimetric SAR data and verifies the effectiveness and advantage of the classification method proposed.

HTML全文

参考文献(1)

Novak L M, Burl M C. Optimal speckle reduction in polarimetric SAR imagery[J].IEEE Trans. on Aerospace Electrical Systems.1990, 26(2):293-305[2]Guoqing Liu, Shunji Huang, Torre A, Rubertone F. The multi-look polarimetric whitening filter for speckle reduction in polarimetric SAR image .IEEE Trans. on Geoscience and Remote Sensing, 1998,363, 36(3) :1016-1020.[3]Mallat S G. A theory for multiresolution signal decomposition: the wavelet representation .IEEE Trans. on Pattern Anal. and Machine Intell, 1989,117, 11(7) :674-693.[4]Daubechies I. The wavelet transform, time-frequency location and signal analysis .IEEE Trans. on Information Theory, 1990,365, 36(5) :961-1005.[5]Besag J. Spatial interaction and the statistical analysis of lattice system .J. Roy. Statist. Soc. B, 1974,362, 36(2) :192-236.[6]Besag J. On the statistical analysis of dirty data .J. Roy. Statist. Soc. B, 1986,483, 48(3) :259-302.[7]Bouman C, Liu B. Multiple resolution segmentation of texture images .IEEE Trans. on Pattern Anal. and Machine Intell, 1991,132, 13(2) :99-113.[8]Geman S, Geman D. Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images .IEEE Trans. on Pattern Anal. and Machine Intell, 1984,66, 6(6) :721-741.[9]Akaik H. A new look at the statistical model identification.IEEE Trans. ou Automat .Control, 1974,196, 19(6) :716-723.[10]Zhang J, Modestino J W, Langan D A. Maximum-likelihood parameter estimation for unsupervised stochastic model-based image segmentation .IEEE Trans. on Image Processing, 1994,34, 3(4) :404-420.[11]Ulaby F T, Elachi C. Radar Polarimetry for Geoscience Applications, Norwood, MA: Artech House Inc, 1990, Chapter 2, 24-25.[12]Srivastava S. On the complex Wishart distribution .Annals of Mathematical Statistics, 1965,362, 36(2) :313-315.[13]Guoqing Liu.[J].Shunji Huang, Torre A, Rubertone F. DuberOptimal multi-look polarimetric speckle reduction and its effect on terrain classification, in Proc. of IGARSS96, Lincoln, NE, USA: July.1515,1996:-

施引文献

资源附件(0)

访问统计