Unsupervised change detection on SAR images using fuzzy hidden Markov chains

被引：103
|
作者：
Carincotte, C [1 ]
Derrode, S [1 ]
Bourennane, S [1 ]
机构：
[1] Inst Fresnel, CNRS, UMR 6133, Dept Multidimens Signal Proc Grp, F-13397 Marseille 20, France
来源：
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2006年 / 44卷 / 02期
关键词：
change detection; fuzzy hidden Markov chain (HMC); iterative conditional estimation (ICE); log-ratio detector; maximal posterior mode (MPM) classification; synthetic aperture radar (SAR) images;
D O I：
10.1109/TGRS.2005.861007
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：
This work deals with unsupervised change detection in temporal sets of synthetic aperture radar (SAR) images. We focus on one of the most widely used change detector in the SAR context, the so-called log-ratio. In order to deal with the classification issue, we propose to use a new fuzzy version of hidden Markov chains (HMCs), and thus to address fuzzy change detection with a statistical approach. The main characteristic of the proposed model is to simultaneously use Dirac and Lebesgue measures at the class chain level. This allows the coexistence of hard pixels (obtained with the classical HNIC segmentation) and fuzzy pixels (obtained with the fuzzy measure) in the same image. The quality assessment of the proposed method is achieved with several bidate sets of simulated images, and comparisons with classical HNIC are also provided. Experimental results on real European Remote Sensing 2 Precision Image (ERS-2 PRI) images confirm the effectiveness of the proposed approach.
引用
收藏
页码：432 / 441
页数：10
相关论文
共 50 条
  • [1] Unsupervised SAR images change detection with hidden Markov chains on a sliding window
    Bouyahia, Zied
    Benyoussef, Lamia
    Derrode, Stephane
    IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XIII, 2007, 6748
  • [2] Unsupervised Change Detection on SAR Images Using Triplet Markov Field Model
    Wang, Fan
    Wu, Yan
    Zhang, Qiang
    Zhang, Peng
    Li, Ming
    Lu, Yunlong
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2013, 10 (04) : 697 - 701
  • [3] Unsupervised classification of radar images using hidden Markov chains and hidden Markov random fields
    Fjortoft, R
    Delignon, Y
    Pieczynski, W
    Sigelle, M
    Tupin, F
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2003, 41 (03): : 675 - 686
  • [4] Unsupervised segmentation of multisensor images using generalized Hidden Markov Chains
    Giordana, N
    Pieczynski, W
    INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, PROCEEDINGS - VOL III, 1996, : 987 - 990
  • [5] Multivariate fuzzy Hidden Markov Chains model applied to unsupervised multiscale SAR image segmentation
    Carincotte, C
    Derrode, S
    Bourennane, S
    FUZZ-IEEE 2005: Proceedings of the IEEE International Conference on Fuzzy Systems: BIGGEST LITTLE CONFERENCE IN THE WORLD, 2005, : 288 - 293
  • [6] Optimized classification approach for SAR images using hidden Markov chains model
    Yuan, L. H.
    Song, J. S.
    Xue, W. T.
    Zheng, Y. A.
    DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES B-APPLICATIONS & ALGORITHMS, 2006, 13E : 1899 - 1903
  • [7] Practical Considerations in Unsupervised Change Detection Using SAR Images
    Ayhan, Bulent
    Kwan, Chiman
    2019 IEEE 10TH ANNUAL UBIQUITOUS COMPUTING, ELECTRONICS & MOBILE COMMUNICATION CONFERENCE (UEMCON), 2019, : 334 - 339
  • [8] Unsupervised Segmentation of SAR Images Using Gaussian Mixture-Hidden Evidential Markov Fields
    Boudaren, Mohamed El Yazid
    An, Lin
    Pieczynski, Wojciech
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2016, 13 (12) : 1865 - 1869
  • [9] Unsupervised change detection in SAR images using a multicomponent HMC model
    Derrode, S
    Mercier, G
    Pieczynski, W
    ANALYSIS OF MULTI-TEMPORAL REMOTE SENSING IMAGES, 2004, 3 : 195 - 203
  • [10] Unsupervised Change Detection in SAR images using Gaussian Mixture Models
    Kiana, E.
    Homayouni, S.
    Sharifi, M. A.
    Farid-Rohani, M.
    INTERNATIONAL CONFERENCE ON SENSORS & MODELS IN REMOTE SENSING & PHOTOGRAMMETRY, 2015, 41 (W5): : 407 - 410
12345