Anomaly Detection in Hyperspectral Images Based on an Adaptive Support Vector Method

Recently, anomaly detection (AD) has attracted considerable interest in a wide variety of hyperspectral remote sensing applications. The goal of this unsupervised technique of target detection is to identify the pixels with significantly different spectral signatures from the neighboring background. Kernel methods, such as kernel-based support vector data description (SVDD) (K-SVDD), have been presented as the successful approach to AD problems. The most commonly used kernel is the Gaussian kernel function. The main problem using the Gaussian kernel-based AD methods is the optimal setting of sigma. In an attempt to address this problem, this paper proposes a direct and adaptive measure for Gaussian K-SVDD (GK-SVDD). The proposed measure is based on a geometric interpretation of the GK-SVDD. Experimental results are presented on real and synthetically implanted targets of the target detection blind-test data sets. Compared to previous measures, the results demonstrate better performance, particularly for subpixel anomalies.

[1]  Marcus S. Stefanou,et al.  A Method for Assessing Spectral Image Utility , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Amit Banerjee,et al.  A support vector method for anomaly detection in hyperspectral imagery , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Lakhmi C. Jain,et al.  Radial Basis Function Networks 2 , 2001 .

[4]  Chunhui Zhao,et al.  An Adaptive Kernel Method for Anomaly Detection in Hyperspectral Imagery , 2008, 2008 Second International Symposium on Intelligent Information Technology Application.

[5]  Heesung Kwon,et al.  Kernel RX-algorithm: a nonlinear anomaly detector for hyperspectral imagery , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Michel Verleysen,et al.  About the locality of kernels in high-dimensional spaces , 2005 .

[7]  John R. Schott,et al.  Comparison of basis-vector selection methods for target and background subspaces as applied to subpixel target detection , 2004, SPIE Defense + Commercial Sensing.

[8]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[9]  Boleslaw K. Szymanski,et al.  Some Properties of the Gaussian Kernel for One Class Learning , 2007, ICANN.

[10]  Ralf Herbrich,et al.  Learning Kernel Classifiers: Theory and Algorithms , 2001 .

[11]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2004 .

[12]  Robert P. W. Duin,et al.  Support Vector Data Description , 2004, Machine Learning.

[13]  Stefania Matteoli,et al.  Different Approaches for Improved Covariance Matrix Estimation in Hyperspectral Anomaly Detection , .

[14]  Lakhmi C. Jain,et al.  Radial basis function networks 1: recent developments in theory and applications , 2001 .

[15]  Robert P. W. Duin,et al.  Support vector domain description , 1999, Pattern Recognit. Lett..

[16]  E. M. Winter,et al.  Anomaly detection from hyperspectral imagery , 2002, IEEE Signal Process. Mag..

[17]  David M. J. Tax,et al.  One-class classification , 2001 .

[18]  José M. F. Moura,et al.  Efficient detection in hyperspectral imagery , 2001, IEEE Trans. Image Process..

[19]  Jun Wang,et al.  A Practical and Robust Way to the Optimization of Parameters in RBF Kernel-Based One-Class Classification Support Vector Methods , 2009, 2009 Fifth International Conference on Natural Computation.

[20]  Jun Wang,et al.  A support vector machine with a hybrid kernel and minimal Vapnik-Chervonenkis dimension , 2004, IEEE Transactions on Knowledge and Data Engineering.

[21]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .