A Time-Efficient Method for Anomaly Detection in Hyperspectral Images

We propose a computationally efficient method for determining anomalies in hyperspectral data. In the first stage of the algorithm, the background classes, which are the dominant classes in the image, are found. The method consists of robust clustering of a randomly chosen small percentage of the image pixels. The clusters are the representatives of the background classes. By using a subset of the pixels instead of the whole image, the computation is sped up, and the probability of including outliers in the background model is reduced. Anomalous pixels are the pixels with spectra that have large relative distances from the cluster centers. Several clustering techniques are investigated, and experimental results using realistic hyperspectral data are presented. A self-organizing map clustered using the local minima of the U-matrix (unified distance matrix) is identified as the most reliable method for background class extraction. The proposed algorithm for anomaly detection is evaluated using realistic hyperspectral data, is compared with a state-of-the-art anomaly detection algorithm, and is shown to perform significantly better.

[1]  Hujun Yin,et al.  Bayesian self-organising map for Gaussian mixtures , 2001 .

[2]  Maria Petrou,et al.  Statistical Assessment for Real-time Background Class Identification in Hyperspectral Images , 2006, 2006 IEEE International Symposium on Geoscience and Remote Sensing.

[3]  E.E. Pissaloux,et al.  Image Processing , 1994, Proceedings. Second Euromicro Workshop on Parallel and Distributed Processing.

[4]  Juha Vesanto,et al.  Neural Network Tool for Data Mining: SOM Toolbox , 2000 .

[5]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  J. Boardman,et al.  Mapping target signatures via partial unmixing of AVIRIS data: in Summaries , 1995 .

[7]  M. Stephens.  Use of the Kolmogorov-Smirnov, Cramer-Von Mises and Related Statistics without Extensive Tables , 1970 .

[8]  Antonio J. Plaza,et al.  Spatial/spectral endmember extraction by multidimensional morphological operations , 2002, IEEE Trans. Geosci. Remote. Sens..

[9]  Iván Machón González,et al.  Self-organizing map and clustering for wastewater treatment monitoring , 2004, Eng. Appl. Artif. Intell..

[10]  Xiaoli Yu,et al.  Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution , 1990, IEEE Trans. Acoust. Speech Signal Process..

[11]  Derek M. Rogge,et al.  Iterative Spectral Unmixing for Optimizing Per-Pixel Endmember Sets , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Keinosuke Fukunaga,et al.  Introduction to statistical pattern recognition (2nd ed.) , 1990 .

[13]  William H. Press,et al.  Numerical recipes in C. The art of scientific computing , 1987 .

[14]  S. J. Sutley,et al.  USGS Digital Spectral Library splib05a , 2003 .

[15]  José M. Bioucas-Dias,et al.  Vertex component analysis: a fast algorithm to unmix hyperspectral data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[16]  A. Burgess.  Comparison of receiver operating characteristic and forced choice observer performance measurement methods. , 1995, Medical physics.

[17]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

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

[19]  Chein-I Chang,et al.  Multispectral and hyperspectral image analysis with convex cones , 1999, IEEE Trans. Geosci. Remote. Sens..

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

[21]  Hairong Qi,et al.  Endmember Extraction From Highly Mixed Data Using Minimum Volume Constrained Nonnegative Matrix Factorization , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Da Ma,et al.  ABUNDANCE EXTRACTIONS FROM AVIRIS IMAGE USING A SELF-ORGANIZING NEURAL NETWORK , 2000 .

[23]  Maria Petrou,et al.  Image processing - dealing with texture , 2020 .

[24]  William H. Press,et al.  Numerical Recipes in FORTRAN - The Art of Scientific Computing, 2nd Edition , 1987 .

[25]  Antonio J. Plaza,et al.  A quantitative and comparative analysis of endmember extraction algorithms from hyperspectral data , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[26]  Geoffrey H. Ball,et al.  ISODATA, A NOVEL METHOD OF DATA ANALYSIS AND PATTERN CLASSIFICATION , 1965 .

[27]  Edward A. Ashton,et al.  Detection of subpixel anomalies in multispectral infrared imagery using an adaptive Bayesian classifier , 1998, IEEE Trans. Geosci. Remote. Sens..

[28]  Liangpei Zhang,et al.  An unsupervised artificial immune classifier for multi/hyperspectral remote sensing imagery , 2006, IEEE Trans. Geosci. Remote. Sens..

[29]  Jo Nothard,et al.  Hyperspectral and broadband FLIR data fusion , 2005, SPIE Security + Defence.

[30]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[31]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[32]  Esa Alhoniemi,et al.  Clustering of the self-organizing map , 2000, IEEE Trans. Neural Networks Learn. Syst..

[33]  Paulo J. G. Lisboa,et al.  Segmentation of the on-line shopping market using neural networks , 1999 .

[34]  Brian S. Penn.  Using self-organizing maps for anomaly detection in hyperspectral imagery , 2002, Proceedings, IEEE Aerospace Conference.

[35]  Mark J. Carlotto,et al.  A cluster-based approach for detecting man-made objects and changes in imagery , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[36]  A. Kashlinsky,et al.  Large-scale structure in the Universe , 1991, Nature.