A new anomaly target detection algorithm for hyperspectral imagery based on optimal band subspaces

Baozhi  Cheng; Chunhui  Zhao

doi:10.6180/jase.202006_23(2).0005

A new anomaly target detection algorithm for hyperspectral imagery based on optimal band subspaces

Electrical Engineering Computer Science and Information Engineering

Baozhi Cheng This email address is being protected from spambots. You need JavaScript enabled to view it.¹and Chunhui Zhao²

¹College of mechanical and electrical engineering, Daqing Normal University, Daqing 163712, China
²College of Information and Communication, Harbin Engineering University, Harbin 150001, China

Received: April 5, 2019
Accepted: January 7, 2020
Publication Date: June 1, 2020

Download Citation: ||https://doi.org/10.6180/jase.202006_23(2).0005

ABSTRACT

In order to overcome low detection accuracy and high false alarm rate of anomaly target detection based on Kernel RX anomaly detector in hyperspectral imagery (HSI). The paper proposes a new HSI anomaly target detection algorithm based on optimal bands subspace that analyses the characteristics of HSI data. First, the wavelet transform method is used to denoise HSI, which makes that the background information of hyperspectral imagery is suppressed by using the advantages of wavelet transform. Then, HSI is divided for band subsets by the classical adaptive subspace method. The optimal bands are selected by using the minimum variance index in each band subsets. Finally, the Kernel RX algorithm is used to detect anomaly target from optimal band subspaces. The data sets of real AVIRIS and synthetic HSI are used in the experiments, and the results show that the proposed algorithm has strong robustness and lower false alarm probability.

Keywords: hyperspectral remote sensing imagery, anomaly target detection, wavelet transform, band subspaces

REFERENCES

[1] Reed, I.S., and Yu, X. (1990) A daptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution, Acoustics, Speech and Signal Processing, IEEE Transactionson 38, 1760-1770.
[2] Zhao, R., Du B., and Zhang, L.P. (2017) Hyperspectral anomaly detection via a sparsity score estimation framework, IEEE Transactions On Geoscience And Remote Sensing 55, 3208-3222.
[3] Maryam, I. (2017) RX anomaly detector with rectified background, IEEE Geoscience and Remote Sensing Letters 14, 1313-1317.
[4] Chang, C.I., and Chiang, S.S. (2002) Anomaly detection and classification for hyperspectral imagery, IEEE Trans. Geosci. Remote Sens 40, 1314-1325.
[5] Guo, Q.D., Zhang, B., and Ran, Q. (2014) Weighted-RXD and linear filter-based RXD: improving background statistics estimation for anomaly detection in hyperspectral imagery, IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens 7, 2351-2366.
[6] Molero, J.M., Paz, A., and Garzón, E.M. (2011) Fast anomaly detection in hyperspectral images with RX method on heterogeneous Clusters, J Supercomput. 58, 411-419.
[7] Schaum, A.P. (2007) Hyperspectral anom- aly detection beyond RX, Proc. SPIE 6565: 656502.
[8] Kwon, H., and Nasrabad, N.M. (2005) Kernel RX-algorithm：a nonlinear anomaly detector for hyperspectral imagery, IEEE Transactions on Geoscience and Remote Sensing 43, 388-397.
[9] Zhao, C.H.，Li, J.W.，and Meng, M.L. (2017) A weighted spatial-spectral kernel rx algorit- hm and efficient implementation on GPUs, Sensors 441, 1-19.
[10] Banerjee, A., Burlina, P., and Diehl, C. (2006) A support vector method for anomaly detection in hyperspectral imagery, IEEE Trans. Geoscience and Remote Sensing 44, 2282-2291.
[11] Yuan, Z.Z., Sun, H., and Ji, K.F. (2014) Local sparsity divergence for hyperspectral anomaly detection, IEEE Geoscience and Remote Sensing Letters 11, 1697-1701.
[12] Li, J.Y., Zhang, H.Y., and Zhang, L.P. (2015) Hyperspectral anomaly detection by the use of background joint sparse representation, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 8, 2523-2532.
[13] Pan, L., Li, H.C., and Deng, Y.J. (2017) Hyperspectral dime- nsionality reduction by tensor sparse and low-rank graph-based discriminant analysis, Remote Sesing 452, 3208-3222.
[14] Xu, Y., Wu, Z.B., and Li, J. (2016) Anomaly detection in hyperspectral images based on low-rank and sparse representation, IEEE Transactions on Geoscience and Remote Sensing 54, 1990-2000.
[15]Noiboar, A., and Cohen, I. (2007) Anomaly detection based on wavelet domain garch random field modeling, IEEE Transactions on Geoscience and Remote Sensing 45, 1361-1373.
[16] Zhang, Y., Zhang, J.P., and Jin, M. (2000) Adaptive subspace decomposition and classification for hyperspectral images, Chinese Journal of Electronics 9, 82-88.
[17] Sheng, Z., Xie, S.Q., and Pan, C.Y. (2001) Probability theory and mathematical statistics, Zhejiang University Press 3, 20-35.
[18] Li, S.S., Zhang, B., and Gao, L.R. (2010) Research of hyperspectral target detection algorithms based on variance minimum, Acta Optica Sinica 30, 2116- 2122 .
[19] Zhao, C.H., LI, J., and Mei, F. (2011) A kernel weighted rx algorithm for anomaly detection in hyperspectral imagery, J.Infrared Millim. Waves 29, 378-382 .
[20] Xu, P., Wang, Z.B., and Zhang, R. (2016) Highly efficient measurement technology based on hyperspectro polarimetric imaging, Chinese J Lasers 43, 0811001 .
[21] Gao, G. (2011) A parzen-window-kernel-based cfar algorithm for ship detection in sar images, IEEE Geoscience and Remote Sensing Letters 8, 557-561.
[22] Maryam, I. (2018) Hyperspectral anomaly detection using differential image, IET Image Process 12, 801-809.
[23] John, E.B., Derek, T.A., and Chee, S.C. (2017) Comprehensive survey of deep learning in remotesensing: theories, tools, and challenges for the community, J. Appl. Remote Sens 11, 042609.
[24] Zhu, L.X., Wen, G.J., and Qiu, S.H.(2018) Low-rank and sparse matrix decomposition with cluster weighting for hyperspectral anomaly detection, Remote Sens. 707, 10050707.
[25] Xu, M.X, Shi, J.Q., and Chen, W. (2018) A band selection method for hyperspectral image based on particle swarm optimization algorithm with dynamic sub-swarms, Journal of Signal Processing Systems 90, 1269-1279.
[26] Angshul, M., Naushad, A., and Hemant, A. (2016) Impulse denoising for hyper-spectral images: A blind compressed sensing approach, Signal Processing 119, 136-141.
[27]Ning Ma, Ximing Yu, and Yu Peng. (2019) A lightweight hyperspectral image anomaly detector for real-time mission, Remote Sens 11, 1622.
[28] Jing Zhang, Lu Chen, and Xi Liang. (2019) Hyperspectral image secure retrieval based on encrypted deep spectral–spatial features, Journal of Applied Remote Sensing 13, 018501.
[29] He, Wei，Li, Zhijun，Chen, and C. L. Philip. (2017) A survey of human-centered intelligent robots: Issues and challenges, IEEE/CAA Journal of Automatica Sinica 4, 602-609.