Immune Clonal Spectral Clustering for PolSAR Land Cover Classification

Abstract:

In this paper, a novel PolSAR land cover classification method is proposed based on spectral clustering (SC) and immune clonal selection principle. SC is employed to reduce dimension in the polarimetric feature space. However, it is susceptible to local optimum and sensitive to the initial partition. To address this issue, immune clonal clustering (ICC) is used due to its capability of global searching. The proposed method combines the complementary advantage of spectral clustering and immune clonal clustering. Experimental results demonstrate that the proposed method is more stable and efficient compared with the other methods.

• Periodical: Applied Mechanics and Materials (Volumes 644-650)
• Pages: 1783-1786
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.644-650.1783
• Online since: September 2014
• Authors: Lu Liu*, Dong Sun, Wen Qing Wang, Rui Can Niu
• Keywords: Clonal Selection, Land Cover Classification, PolSAR, Spectral Clustering

References

[1] P. Yu, A.K. Qin, D.A. Clausi, Unsupervised Polarimetric SAR Image Segmentation and Classification Using Region Growing With Edge Penalty, IEEE Transactions on Geoscience and Remote Sensing, 50(4) (2012) 1302-1317.

DOI: 10.1109/tgrs.2011.2164085

[2] J.S. Lee, M.R. Grunes, T.L. Ainsworth, et al, Unsupervised classification using polarimetric decomposition and the complex Wishart classifier, IEEE Transactions on Geoscience and Remote Sensing, 37(5) (1999) 2249-2258.

DOI: 10.1109/36.789621

[3] B. Liu, W.X. Yu, et al, Superpixel-Based Classification With an Adaptive Number of Classes for Polarimetric SAR Images, IEEE Transactions on Geoscience and Remote Sensing, 51(2) (2013) 907-924.

DOI: 10.1109/tgrs.2012.2203358

[4] C. Fowlkes, S. Belongie, et al, Spectral grouping using the Nystrom method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(2) (2004) 214-225.

DOI: 10.1109/tpami.2004.1262185

[5] F.M. Burnet. The Clonal Selection Theory of Acquired Immunity, Cambridge University Press, (1959).

[6] L.C. Jiao, H.F. Du, Development and Prospect of the Artificial Immune System, Acta Electronica Sinica, 31 (2003) 73-80.

[7] J.S. Lee, M.R. Grunes, T. L. Ainsworth, et al, Unsupervised classification using polarimetric decomposition and the complex Wishart classifier. IEEE Transactions on Geoscience and Remote Sensing, 37(5) (1999) 2249-2258.

DOI: 10.1109/36.789621

[8] S.N. Anfinsen, R. Jenssen, T. Eltoft, Spectral clustering of polarimetric SAR data with Wishart-derived distance measures, in Proc. POLinSAR, 7(2007).

[9] H.F. Du, Adaptive dynamic clone selection algorithm. International Conference on Rough Sets and Current Trends in Computing Uppsala, Sweden, (2004)768-773.

DOI: 10.1007/978-3-540-25929-9_97

[10] M.K. Pakhira, S. Bandyopadhyay, U. Maulik, Validity index for crisp and fuzzy clusters, Pattern Recognition, 3(37) (2004) 487-501.

DOI: 10.1016/j.patcog.2003.06.005