Improving Wishart Classification of Polarimetric SAR Data Using the Hopfield Neural Network Optimization Approach

被引:17
作者
Pajares, Gonzalo [1 ]
Lopez-Martinez, Carlos [2 ]
Javier Sanchez-Llado, F. [2 ]
Molina, Inigo [3 ]
机构
[1] Univ Complutense Madrid, Fac Informat, E-28040 Madrid, Spain
[2] Univ Politecn Cataluna, Signal Theory & Commun Dept TSC, Remote Sensing Lab RSLab, ES-08034 Barcelona, Spain
[3] Tech Univ Madrid, ETSITGC, Madrid 28031, Spain
关键词
Hopfield neural networks; image classification; Polarimetric Synthetic Aperture Radar (PolSAR); Wishart classifier; optimization; UNSUPERVISED CLASSIFICATION; FUZZY CLASSIFICATION; ASSOCIATIVE MEMORY; DECOMPOSITION;
D O I
10.3390/rs4113571
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
This paper proposes the optimization relaxation approach based on the analogue Hopfield Neural Network (HNN) for cluster refinement of pre-classified Polarimetric Synthetic Aperture Radar (PolSAR) image data. We consider the initial classification provided by the maximum-likelihood classifier based on the complex Wishart distribution, which is then supplied to the HNN optimization approach. The goal is to improve the classification results obtained by the Wishart approach. The classification improvement is verified by computing a cluster separability coefficient and a measure of homogeneity within the clusters. During the HNN optimization process, for each iteration and for each pixel, two consistency coefficients are computed, taking into account two types of relations between the pixel under consideration and its corresponding neighbors. Based on these coefficients and on the information coming from the pixel itself, the pixel under study is re-classified. Different experiments are carried out to verify that the proposed approach outperforms other strategies, achieving the best results in terms of separability and a trade-off with the homogeneity preserving relevant structures in the image. The performance is also measured in terms of computational central processing unit (CPU) times.
引用
收藏
页码:3571 / 3595
页数:25
相关论文
共 35 条
[1]  
[Anonymous], 1992, Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence
[2]  
[Anonymous], 1994, Neural networks: a comprehensive foundation
[3]  
Benz U, 2001, INT GEOSCI REMOTE SE, P1427, DOI 10.1109/IGARSS.2001.976867
[4]  
Cloude S.R., 1997, SPIE, V3120, P132, DOI DOI 10.1117/12.278958
[5]   An entropy based classification scheme for land applications of polarimetric SAR [J].
Cloude, SR ;
Pottier, E .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1997, 35 (01) :68-78
[6]   A review of target decomposition theorems in radar polarimetry [J].
Cloude, SR ;
Pottier, E .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1996, 34 (02) :498-518
[7]   ABSOLUTE STABILITY OF GLOBAL PATTERN-FORMATION AND PARALLEL MEMORY STORAGE BY COMPETITIVE NEURAL NETWORKS [J].
COHEN, MA ;
GROSSBERG, S .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1983, 13 (05) :815-826
[8]   Three-Component Power Decomposition for Polarimetric SAR Data Based on Adaptive Volume Scatter Modeling [J].
Cui, Yi ;
Yamaguchi, Yoshio ;
Yang, Jian ;
Park, Sang-Eun ;
Kobayashi, Hirokazu ;
Singh, Gulab .
REMOTE SENSING, 2012, 4 (06) :1559-1572
[9]   CLUSTER SEPARATION MEASURE [J].
DAVIES, DL ;
BOULDIN, DW .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1979, 1 (02) :224-227
[10]   Analysis by Wavelet Frames of Spatial Statistics in SAR Data for Characterizing Structural Properties of Forests [J].
De Grandi, Gianfranco D. ;
Lucas, Richard M. ;
Kropacek, Jan .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2009, 47 (02) :494-507