Unsupervised SAR Image Segmentation Using a Hierarchical TMF Model

被引：11
|
作者：
Zhang, Peng [1 ]
Li, Ming [1 ]
Wu, Yan [2 ]
Liu, Gaofeng [1 ]
Chen, Hongmeng [1 ]
Jia, Lu [1 ]
机构：
[1] Xidian Univ, Natl Key Lab Radar Signal Proc, Xian 710071, Peoples R China
[2] Xidian Univ, Sch Elect Engn, Remote Sensing Image Proc & Computat Grp, Xian 710071, Peoples R China
来源：
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2013年 / 10卷 / 05期
关键词：
Bayesian inference; hierarchical triplet Markov field (HTMF) model; multiclass segmentation; synthetic aperture radar (SAR) image; MULTICLASS SEGMENTATION;
D O I：
10.1109/LGRS.2012.2227295
中图分类号：
P3 [地球物理学]; P59 [地球化学];
学科分类号：
0708 ; 070902 ;
摘要：
The triplet Markov field (TMF) model recently proposed is suitable for tackling the nonstationary image segmentation. In this letter, we propose a hierarchical TMF (HTMF) model for unsupervised synthetic aperture radar (SAR) image segmentation. In virtue of the Bayesian inference on the quadtree, the HTMF model captures the global and local image characteristics more precisely in the bottom-up and top-down probability computations. In this way, the underlying spatial structure information is effectively propagated. To model the SAR data related to radar backscattering sources, generalized Gamma distribution is utilized. The effectiveness of the proposed HTMF model is demonstrated by application to simulated data and real SAR image segmentation.
引用
收藏
页码：971 / 975
页数：5
相关论文
共 50 条
  • [41] An efficient unsupervised mixture model for image segmentation
    Lin, Pan
    Zheng, XiaoJian
    Yu, Gang
    Weng, ZuMao
    Cai, Sheng Zhen
    [J]. NEURAL INFORMATION PROCESSING, PT 2, PROCEEDINGS, 2006, 4233 : 379 - 386
  • [42] Unsupervised SAR Image Segmentation Based on Conditional Triplet Markov Fields
    Lian, Xiaojie
    Wu, Yan
    Zhao, Wei
    Wang, Fan
    Zhang, Qiang
    Li, Ming
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2014, 11 (07) : 1185 - 1189
  • [43] Unsupervised SAR image segmentation using high-order conditional random fields model based on product-of-experts
    Zhang, Peng
    Li, Ming
    Wu, Yan
    An, Lin
    Jia, Lu
    [J]. PATTERN RECOGNITION LETTERS, 2016, 78 : 48 - 55
  • [44] Texture segmentation of SAR image using multiresolution pairwise Markov model
    Liu, Bao-Li
    [J]. PROCEEDINGS OF THE INTERNATIONAL CONFERENCE INFORMATION COMPUTING AND AUTOMATION, VOLS 1-3, 2008, : 1348 - 1351
  • [45] MPM SAR Image Segmentation Using Feature Extraction and Context Model
    Hou, Biao
    Zhang, Xiangrong
    Li, Nan
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2012, 9 (06) : 1041 - 1045
  • [46] SAR Image Segmentation Based on Hierarchical Visual Semantic and Adaptive Neighborhood Multinomial Latent Model
    Liu, Fang
    Duan, Yiping
    Li, Lingling
    Jiao, Licheng
    Wu, Jie
    Yang, Shuyuan
    Zhang, Xiangrong
    Yuan, Jialin
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (07): : 4287 - 4301
  • [47] Adaptive Hierarchical Multinomial Latent Model With Hybrid Kernel Function for SAR Image Semantic Segmentation
    Duan, Yiping
    Liu, Fang
    Jiao, Licheng
    Tao, Xiaoming
    Wu, Jie
    Shi, Cheng
    Wimmers, Martin Onno
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2018, 56 (10): : 5997 - 6015
  • [48] Unsupervised hierarchical image segmentation with level set and additive operator splitting
    Jeon, M
    Alexander, M
    Pedrycz, W
    Pizzi, N
    [J]. PATTERN RECOGNITION LETTERS, 2005, 26 (10) : 1461 - 1469
  • [49] Unsupervised Texture-Based SAR Image Segmentation Using Spectral Regression and Gabor Filter Bank
    Tirandaz, Zeinab
    Akbarizadeh, Gholamreza
    [J]. JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING, 2016, 44 (02) : 177 - 186
  • [50] Unsupervised Texture-Based SAR Image Segmentation Using Spectral Regression and Gabor Filter Bank
    Zeinab Tirandaz
    Gholamreza Akbarizadeh
    [J]. Journal of the Indian Society of Remote Sensing, 2016, 44 : 177 - 186
12345