Triplet Markov fields with edge location for fast unsupervised multi-class segmentation of synthetic aperture radar images

被引:13
作者
Gan, L. [1 ]
Wu, Y. [1 ]
Liu, M. [1 ]
Zhang, P. [2 ]
Ji, H. [1 ]
Wang, F. [1 ]
机构
[1] Xidian Univ, Sch Elect Engn, Xian 710071, Peoples R China
[2] Xidian Univ, Natl Key Lab Radar Signal Proc, Xian 710071, Peoples R China
基金
中国国家自然科学基金;
关键词
ALGORITHM; MPM;
D O I
10.1049/iet-ipr.2011.0198
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Triplet Markov fields (TMF) model is suitable for dealing with multi-class segmentation of non-stationary synthetic aperture radar (SAR) images. In this study, an algorithm using TMF with edge location for fast unsupervised multi-class segmentation of SAR images is proposed. The new segmentation algorithm can locate edge accurately with reasonable computational cost. First for the statistical characteristics of multiplicative speckle noise in SAR image, an edge strength based on the ratio of exponentially weighted averages operator is introduced into the Turbopixels algorithm to obtain a superpixel graph with accurate edge location in SAR images. To enhance the computational efficiency and suppress the speckle, the TMF model on pixel is generalised to that on the superpixel graph. Then, the new corresponding potential energy function and maximisation of posterior marginal segmentation formula are derived. The experimental results on synthetic and real SAR images show that the proposed algorithm can obtain accurate edge location in multi-class segmentation of SAR images, as well as enhance the computational efficiency. Especially when dealing with SAR images in large size, the proposed algorithm can give a robust and efficient result of segmentation.
引用
收藏
页码:831 / 838
页数:8
相关论文
共 19 条
[1]   Unsupervised image segmentation using triplet Markov fields [J].
Benboudjema, D ;
Pieczynski, W .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2005, 99 (03) :476-498
[2]  
Benboudjema D, 2007, INT GEOSCI REMOTE SE, P3891
[3]   Unsupervised statistical segmentation of nonstationary images using triplet Markov fields [J].
Benboudjema, Dalila ;
Pieczynski, Wojciech .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2007, 29 (08) :1367-1378
[4]   An unsupervised segmentation method based on MPM for SAR images [J].
Cao, YF ;
Sun, H ;
Xu, X .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2005, 2 (01) :55-58
[5]   Quantitative comparison of the performance of SAR segmentation algorithms [J].
Caves, R ;
Quegan, S ;
White, R .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1998, 7 (11) :1534-1546
[6]   Mean shift: A robust approach toward feature space analysis [J].
Comaniciu, D ;
Meer, P .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (05) :603-619
[7]   The EM/MPM algorithm for segmentation of textured images: Analysis and further experimental results [J].
Comer, ML ;
Delp, EJ .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2000, 9 (10) :1731-1744
[8]   Efficient graph-based image segmentation [J].
Felzenszwalb, PF ;
Huttenlocher, DP .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 59 (02) :167-181
[9]   An optimal multiedge detector for SAR image segmentation [J].
Fjortoft, R ;
Lopes, A ;
Marthon, P ;
Cubero-Castan, E .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1998, 36 (03) :793-802
[10]   Unsupervised Synthetic Aperture Radar Image Segmentation Using Fisher Distributions [J].
Galland, Frederic ;
Nicolas, Jean-Marie ;
Sportouche, Helene ;
Roche, Muriel ;
Tupin, Florence ;
Refregier, Philippe .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2009, 47 (08) :2966-2972