UNSUPERVISED POLSAR IMAGE CLASSIFICATION USING BOUNDARY-PRESERVING REGION DIVISION AND REGION-BASED AFFINITY PROPAGATION CLUSTERING

被引：0
作者：
Hou, Biao [1 ]
Jiang, Yuheng [1 ]
Ren, Bo [1 ]
Wen, Zaidao [1 ]
Wang, Shuang [1 ]
Jiao, Licheng [1 ]
机构：
[1] Xidian Univ, Key Lab Intelligent Percept & Image Understanding, Minist Educ China, Xian, Peoples R China
来源：
2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS) | 2016年
基金：
中国国家自然科学基金;
关键词：
Polarimetric SAR; Image classification; Boundary preservation; Affinity propagation clustering; POLARIMETRIC SAR IMAGES; ADAPTIVE NUMBER; DECOMPOSITION; SEGMENTATION; FRAMEWORK; SPACE;
D O I：
10.1109/IGARSS.2016.7730330
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
This paper presents a new method for polarimetric synthetic aperture radar (PolSAR) image classification. Firstly, to get a reasonable edge strength map, polarimetric information is used in edge strength calculation, and watershed algorithm is used to obtain the oversegmentation using the edge strength. Secondly, a searching table is used to determine the most suitable region to be merged. Finally, region-based affinity propagation clustering is employed to achieve an initial classification map, and the method provides an adjacent Wishart classifier with spatial relations to obtain the final classification result.
引用
收藏
页码：5103 / 5106
页数：4
相关论文
共 17 条
  • [1] A Textural-Contextual Model for Unsupervised Segmentation of Multipolarization Synthetic Aperture Radar Images
    Akbari, Vahid
    Doulgeris, Anthony P.
    Moser, Gabriele
    Eltoft, Torbjorn
    Anfinsen, Stian N.
    Serpico, Sebastiano B.
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2013, 51 (04): : 2442 - 2453
  • [2] [Anonymous], 2008, Image Processing, Analysis, and Machine Vision
  • [3] A Generic Land-Cover Classification Framework for Polarimetric SAR Images Using the Optimum Touzi Decomposition Parameter Subset-An Insight on Mutual Information-Based Feature Selection Techniques
    Banerjee, Biplab
    Bhattacharya, Avik
    Buddhiraju, Krishna Mohan
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2014, 7 (04) : 1167 - 1176
  • [4] An unsupervised segmentation with an adaptive number of clusters using the SPAN/H/α/A space and the complex Wishart clustering for fully polarimetric SAR data analysis
    Cao, Fang
    Hong, Wen
    Wu, Yirong
    Pottier, Eric
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2007, 45 (11): : 3454 - 3467
  • [5] Automated Non-Gaussian Clustering of Polarimetric Synthetic Aperture Radar Images
    Doulgeris, Anthony P.
    Anfinsen, Stian Normann
    Eltoft, Torbjorn
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2011, 49 (10): : 3665 - 3676
  • [6] Clustering by passing messages between data points
    Frey, Brendan J.
    Dueck, Delbert
    [J]. SCIENCE, 2007, 315 (5814) : 972 - 976
  • [7] Evolutionary RBF classifier for polarimetric SAR images
    Ince, Turker
    Kiranyaz, Serkan
    Gabbouj, Moncef
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2012, 39 (05) : 4710 - 4717
  • [8] Unsupervised classification using polarimetric decomposition and the complex Wishart classifier
    Lee, JS
    Grunes, MR
    Ainsworth, TL
    Du, LJ
    Schuler, DL
    Cloude, SR
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1999, 37 (05): : 2249 - 2258
  • [9] Unsupervised terrain classification preserving polarimetric scattering characteristics
    Lee, JS
    Grunes, MR
    Pottier, E
    Ferro-Famil, L
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2004, 42 (04): : 722 - 731
  • [10] Polarimetric SAR speckle filtering and its implication for classification
    Lee, JS
    Grunes, MR
    de Grandi, G
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1999, 37 (05): : 2363 - 2373
12