采用联合相似度谱聚类集成的极化SAR分类

doi:10.3969/j.issn.1001-2400.2015.03.009

Abstract

Abstract:

In order to improve the robustness of spectral clustering to the scaling parameter and avoid the instable results caused by the Nystrm approximation, a novel spectral clustering ensemble method for Polarimetric SAR (PolSAR) land cover classification is proposed. Firstly, Wishart-derived distance measure and polarimetric similarity are combined to obtain the complementary information from the spatial and polarimetric relations between pairwise pixels. The Markov Random Field (MRF) potential function is introduced to construct the similarity matrix. Then the Nystrm approximation based spectral clustering is employed to achieve a single spectral classification of PolSAR data. Finally, multiple individual classifications are obtained and integrated by an ensemble strategy. Experimental results demonstrate that the proposed method improves the classification performance and region harmony, and leads to stable results.

Key words: polarimetric synthetic aperture radar, spectral clustering ensemble, Wishart distance, MRF

CLC Number:

TP75

LIU Lu;WANG Rongfang;JIAO Licheng;SHI Junfei. Combined similarity based spectral clustering ensemble for POLSAR classification[J].J4, 2015, 42(3): 48-53+128.

References

［1］ He C, Zhuo T, Ou D, et al. Nonlinear Compressed Sensing-based LDA Topic Model for Polarimetric SAR Image Classification ［J］. IEEE Journal of Selected Topics in Applied Earth Observation and Remote Sensing, 2014, 7(3): 972-982.
［2］ Niu X, Ban Y F. A Novel Contextual Classification Algorithm for Multitemporal Polarimetric SAR Data［J］. IEEE Geoscience and Remote Sensing Letters, 2014, 11(3): 681-685.
［3］ Lee J S, Grunes M R, Pottier E, et al. Unsupervised Terrain Classification Preserving Polarimetric Scattering Characteristics ［J］. IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(4): 722-731.
［4］ Wang S, Liu K, Pei J J, et al. Unsupervised Classification of Fully Polarimetric SAR Images Based on Scattering Power Entropy and Copolarized Ratio［J］. IEEE Geoscience and Remote Sensing Letters, 2013, 10 (3): 622-626.
［5］ Yu P, Qin A K, Clausi D A. Unsupervised Polarimetric SAR Image Segmentation and Classification Using Region Growing with Edge Penalty ［J］. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(4): 1302-1317.
［6］ Liu B, Hu H, Wang H Y, et al. Superpixel-based Classification with an Adaptive Number of Classes for Polarimetric SAR Images ［J］. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(2): 907-924.
［7］ Lang F K, Yang J, Li D R, et al. Polarimetric SAR Image Segmentation Using Statistical Region Merging［J］. IEEE Geoscience and Remote Sensing Letters, 2014, 11(2): 509-513.
［8］刘逸, 寇卫东, 慕彩虹. 结合多阈值法的模糊聚类用于SAR图像变化检测［J］. 西安电子科技大学学报, 2013, 40(6): 13-18.
Liu Yi, Kou Weidong, Mu Caihong. Change Detection for SAR Images Based on Fuzzy Clustering Using Multilevel Thresholding［J］. Journal of Xidian University, 2013, 40(6): 13-18.
［9］ Anfinsen S N, Jenssen R, Eltoft T. Spectral Clustering of Polarimetric SAR Data with Wishart-derived Distance Measures ［C］//Proceedings of PolInSAR: 3rd International Workshop on Science and Applications of SAR Polarimetry and Polarimetric Interferometry. Noorduijk: Europecom Space Agency, 2007: SP-644.
［10］ Ersahin K, Gumming I G, Ward R K. Segmentation and Classification of Polarimetric SAR Data Using Spectral Graph Partitioning ［J］. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(1): 164-174.
［11］李旭, 林伟. 基于极化相似性特征的极化SAR图像的谱分类［J］. 计算机应用, 2010, 30(5): 1415-1417.
Li Xu, Lin Wei. Spectral Classification of Polarimetric SAR Images Based on Polarimetric Similarity ［J］. Journal of Computer Application, 2010, 30(5): 1415-1417.
［12］ Freeman A, Durden S L. A Three-component Scattering Model for Polarimetric SAR Data ［J］. IEEE Transactions on Geoscience and Remote Sensing, 1998, 36(3): 963-973.
［13］ Hou Y M, Lun X M, Meng W, et al. Unsupervised Segmentation Method for Color Image Based on MRF ［C］//International Conference on Computational Intelligence and Natural Computing: 1. Piscataway: IEEE, 2009: 174-177.
［14］ Huber P J. Robust Statistics ［M］. Berlin: Springer, 2011: 1248-1251.
［15］ Zhang X R, Jiao L C, Liu F, et al. Spectral Clustering Ensemble Applied to SAR Image Segmentation ［J］. IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(7): 2126-2136.
［16］ Fowlkes C, Belongie S, Fan Chung, et al. Spectral Grouping Using the Nystrm Method ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(2): 214-225.
［17］ Strehl A, Ghosh J. Cluster Ensembles—a Knowledge Reuse Framework for Combining Multiple Partitions ［J］.The Journal of Machine Learning Research, 2003, 3(3): 583-617.

[1]	SUN Chen, CHENG Liye. Spatial sensing matrix learning for PolSAR image classification [J]. Journal of Xidian University, 2018, 45(6): 92-98.
[2]	ZHANG Shuyin;HOU Biao. POLSAR image classification via high-probability selection and adaptive MRF [J]. Journal of Xidian University, 2017, 44(6): 59-64.
[3]	LU Hongxi;LI Donglin;LIU Hongwei;SUO Zhiyong;SONG Wenqing;BAO Zheng. Forest parameters retrieval with dual-baseline polarimetric SAR interferometry based on clustering analysis [J]. J4, 2015, 42(6): 23-29.
[4]	CHEN Bo;WANG Shuang;JIAO Licheng;LIU Fang;MAO Shasha. Polarimetric SAR image classification via naive Bayes combination [J]. J4, 2015, 42(2): 45-51.
[5]	CUI Haogui;LIU Tao;SHAN Hongchang;JIANG Yuzhong;GAO Jun . Novel statistical model recognition method for PolSAR imagery [J]. J4, 2015, 42(2): 199-205.

Combined similarity based spectral clustering ensemble for POLSAR classification

PDF (PC)

Like

Knowledge

Cited

Abstract

Cite this article

share this article

References

Related Articles 5

Metrics

Comments

Recommended 0