Anomaly Detection in Hyperspectral Imagery Based on Spectral Dimensions Transformation and Spatial Filter

Baozhi  Cheng; Jianpei  Zhang

doi:10.6180/jase.2017.20.1.13

Anomaly Detection in Hyperspectral Imagery Based on Spectral Dimensions Transformation and Spatial Filter

Computer Science and Information Engineering

Baozhi Cheng ^1,2 and Jianpei Zhang¹

¹College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, P.R. China
²College of Mechanical and Electrical Engineering, Daqing Normal University, Daqing 163712, P.R. China

Received: October 12, 2015
Accepted: October 20, 2016
Publication Date: March 1, 2017

Download Citation: ||https://doi.org/10.6180/jase.2017.20.1.13

ABSTRACT

In this paper, a novel anomaly detection algorithm is proposed for hyperspectral imagery, which is the extended RX algorithm based on spectral dimension transformation and spatial filter (STSF-RX). Firstly, minimum noise fraction (MNF) transform is performed on the original hyperspectral images, by setting a SNR threshold, and obtains MNF transform matrices that the SNR of their corresponding bands are larger than the threshold. Then, for suppressing background interferences, orthogonal subspace projection (OSP) is estabished by MNF transform matrices, and project the hyperspectral data of MNF transform to the OSP, and obtain the error data of hyperspectral. In order to concentrate the energy of detection targets in first a few components, principal components analysis (PCA) method is performed on the processing hyperspectral image. Finally, we obtain bands for PCA transform based on the eigenvalue threshold, the eigenvalue of the bands are larger than threshold, and the bands are input to the RX detector. The simulation results demonstrate that the proposed STSF-RX algorithm outperforms the others algorithm, it is higher precision and lower false alarm probability; especially, the computation time of the proposed algorithm is very short.

Keywords: Hyperspectral Images Processing, Hyperspectral Anomaly Detection, Spectral Dimensions Transformation

REFERENCES

[1] Du, B. and Zhang, L. P., “Random-Selection-Based Anomaly Detector for Hyperspectral Imagery,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 49, No. 5, pp. 15781589 (2011). doi: 10.1109/TGRS. 2010.2081677
[2] Qi, B., Zhao, C. H., Youn, E. and Nansen, C., “Use of Weighting Algorithms to Improve Traditional Support Vector Machine Based Classifications of Reflectance Data,” Optics Express, Vol. 19, No. 27, pp. 26816 26826 (2011). doi: 10.1364/OE.19.026816
[3] Reed, I. S. and Yu, X., “Adaptive Multiple-band CFAR Detection of an Optical Pattern with Unknown Spectral Distribution,” IEEE Trans. Acoust., Speech Signal Process., Vol. 38, No. 10, pp. 17601770 (1990). doi: 10.1109/29.60107
[4] Kwon, H. and Nasrabad, N. M., “Kernel RX-algorithm: a Nonlinear Anomaly Detector for Hyperspectral Imagery,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 43, No. 2, pp. 388397 (2005). doi: 10.1109/TGRS.2004.841487
[5] Matteoli, S., Diani, M. and Corsini, G., “Improved Estimation of Local Background Covariance Matrix for Anomaly Detection in Hyperspectral Images,” Opt. Eng., Vol. 49, No. 4, p. 046201 (2010). doi: 10.1117/1.3386 069
[6] Acito, N., Diani, M. and Corsini, G., “On the CFAR Property of the RX Algorithm in the Presence of Signal-dependent Noise in Hyperspectral Images,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 51, No. 6, pp. 34753491 (2013). doi: 10.1109/TGRS. 2012.2221128
[7] Stefania, M., Tiziana, V., Marco, D., et al., “A Locally Adaptive Background Density Estimator: an Evolution for RX-Based Anomaly Detectors,” IEEE Geoscience and Remote Sensing Letters, Vol. 11, No. 1, pp. 323 327 (2014). doi: 10.1109/LGRS.2013.2257670
[8] Banerjee, A., Burlina, P. and Dieh, C., “A Support Vector Method for Anomaly Detection in Hyperspectral Imagery,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 44, No. 8, pp. 22822291 (2006). doi: 10.1109/TGRS.2006.873019
[9] Zhao, C. H., You, J., Qi, B., et al., “Real-time Anomaly Detection Algorithm for Hyperspectral Remote Sensing by Using Recursive Polynomial Kernel Function,” Acta Optica Sinica, Vol. 36, No. 2, p. 0228002 (2016). doi: 10.3788/AOS201636.0228002
[10] Li, W. and Du, Q., “Collaborative Representation for Hyperspectral Anomaly Detection,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 5, No. 1, pp. 4347, pp. 14631474 (2015). doi: 10.1109/TGRS. 2014.2343955
[11] Chen, H. T., “Anomaly Detection SVDD Algorithm Based on Nonsubsampled Contourlet Transform,” Infrared Technology, Vol. 38, No. 1, pp. 4752 (2016).
[12] Ergul, M., Sen, N. and Okman, O. E., “Effective Training Set Sampling Strategy for SVDD Anomaly Detection in Hyperspectral Imagery,” Proc. SPIE 9088, Algorithms and Technologies for Multispectral, Hyperspectral and Ultraspectral Imagery, Vol. 9088, 908815 (2014). doi: 10.1117/12.2051040
[13] Yuan, Z. Y., Sun, H., Ji, K. F., et al., “Local Sparsity Divergence for Hyperspectral Anomaly Detection,” IEEE Geoscience and Remote Sensing Letters, Vol. 11, No. 10, pp. 16971701 (2014). doi: 10.1109/LGRS. 2014.2306209
[14] Zhang, L. L., Zhao, C. H. and Cheng, B. Z., “A Joint Kernel Collaborative Representation Based Approach for Hyperspectral Image Anomaly Target Detection,” Journal of Optoelectronics·Laser, Vol. 26, No. 11, pp. 21542161 (2015).
[15] Xu, Y., Wu, Z. B. and Li, J., “Anomaly Detection in Hyperspectral Images Based on Low-rank and Sparse Representation,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 54, No. 4, pp. 19902000 (2015). doi: 10.1109/TGRS.2015.2493201
[16] Gu, Y. F., Liu, Y. and Zhang, Y., “A Selective Kpca Algorithm Based on High-order Statistics for Anomaly Detection in Hyperspectral Imagery,” IEEE Geoscience and Remote Sensing Letters, Vol. 5, No. 1, pp. 4347 (2008). doi: 10.1109/LGRS.2007.907304
[17] Bioucas-Dias, J. M. and Nascimento, J. M. P., “Hyperspectral Subspace Identification,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 46, No. 8, pp. 24352445 (2008). doi: 10.1109/TGRS.2008.918089
[18] Berman, M., Kiiveri, H., Lagerstrom, R., Ernst, A., Dunne, R. and Huntington, J. F., “ICE: a Statistical Approach to Identifying Endmembers in Hyperspectral Images,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 42, No. 10, pp. 20852095 (2004). doi: 10.1109/TGRS.2004.835299
[19] Chang, C. I. and Du, Q., “Interference Andnoise-adjusted Principal Components Analysis,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 37, No. 5, pp. 23872396 (1999). doi: 10.1109/36.789637
[20] Chen, G. Y. and Qian, S. E., “Denoising of Hyperspectral Imagery Using Principal Component Analysis and Wavelet Shrinkage,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 49, No. 3, pp. 973 980 (2011). doi: 10.1109/TGRS.2010.2075937
[21] Jablonski, J. A., Bihl, T. J. and Kenneth, W., “Principal Component Reconstruction Error for Hyperspectral Anomaly Detection,” IEEE Geoscience and Remote Sensing Letters, Vol. 12, No. 8, pp. 17251729 (2015). doi: 10.1109/LGRS.2015.2421813
[22] M. D. Jr, Mersereau, R. M., “On the Impact of PCA Dimension Reduction for Hyperspectral Detection of Difficult Targets,” IEEE Geoscience and Remote Sensing Letters, Vol. 2, No. 2, pp. 1921995 (2005). doi: 10.1109/LGRS.2005.846011
[23] Prasad, S. and Mann Bruce, L., “Limitations of Principal Component Analysis for Hyperspectral Target Recognition,” IEEE Geoscience and Remote Sensing Letters, Vol. 5, No. 4, pp. 625629 (2008). doi: 10.1109/ LGRS.2008.2001282
[24] Acito, N., Diani, M. and Corsini, G., “A New Algorithm for Robust Estimation of the Signal Subspacein Hyperspectral Images In the Presence of Rare Signal Components,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 47, No. 11, pp. 38443856 (2009). doi: 10.1109/TGRS.2009.2021764
[25] Matteoli, S., Diani, M. and Corsini, G., “A Tutorial Overview of Anomaly Detection in Hyperspectral Images,” IEEE Aerosp. Electron. Syst. Mag. Tutorials, Vol. 25, No. 7, pp. 528 (2010). doi: 10.1109/MAES. 2010.5546306
[26] Gu, Y. F., Research on Classification And Target Detection Technique With Kernel Method for Hyperspectral Images, Ph.D Dissertation, Harbin Institute of Technology. pp. 93106 (2005).
[27] Gu, Y. F., Liu, Y., Jia, Y. H. and Zhang, Y., “Anomaly Detection Algorithm of Hyperspectral Images Based on Spectral Analyses,” J. Infrared Millim. Waves, Vol. 26, No. 6, pp. 473477 (2006).
[28] Zhao, C. H., Li, J. and Mei, F., “A Kernel Weighted RX Algorithm for Anomaly Detection in Hyperspectral Imagery,” J. Infrared Millim. Waves, Vol. 29, No. 5, pp. 378382 (2011). doi: 10.3724/SP.J.1010.2010.00 378
[29] Hazai, S. K., Safari, A., Mojaradi, B. and Homayouni, S., “A Fast-adaptive Support Vector Method for Fullpixel Anomaly Detection in Hyperspectral Images,” 2011 IEEE Geoscience and Remote Sensing Society, Canada: Vancourer, pp. 17631766 (2011). doi: 10. 1109/IGARSS.2011.6049461
[30] Miao, L. D. and Qi, H. R., “Endmember Extraction from Highly Mixed Data Using Minimum Volume Constrained Nonnegative Matrix Factorization,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 45, No. 3, pp. 765777 (2007). doi: 10.1109/TGRS. 2006.888466
[31] Zhao, C. H., Jing, X. H. and Li, W., “Hyperspectral Imagery Target Detection Algorithm Based on StOMP Sparse Representation,” Journal of Harbin Engineering University, Vol. 36, No.7, pp. 992996 (2015).
[32] Chang, C. C., Ren, H., Chang, C. I., et al., “How to Design Synthetic Images to Validate and Evaluate Hyperspectral Imaging Algorithms,” Proc. SPIE 6966, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII, Orlando, U.S.A., Mar. 16 (2008). doi: 10.1117/12.777717