Abstract
To solve the low detection efficiency problem of Constrained Energy Minimization (CEM) method used for hyperspectral remote sensing imagery, this paper firstly presents two improved detection methods: principal component CEM (PCCEM) and matrix taper CEM (MTCEM). Then, based on these two methods, a more optimized Two-Time detection (TTD) method is proposed. Primarily, the targets of interest in the hyperspectral image are detected by using the PCCEM and MTCEM method. Then the autocorrelation matrix of non-target pixels is estimated according to the target detection results. Finally, based on this autocorrelation matrix, a new weight vector is constructed for the second detection. Under the effect of this new weight vector, the output energy of the target can be kept at unity and the output energy of the background is suppressed at the same time. Then, the improvement of target detection result can be realized. Experimental results on a real world hyperspectral data show the efficiency of the proposed TTD method to improve the detection performance.
Similar content being viewed by others
References
Behrens, R. T., & Scharf, L. L. (1994). Signal processing applications of oblique projection operators. IEEE Transactions on Signal Processing, 42(6), 1413–1424.
Gao, L. R., Yang, B., Du, Q., & Zhang, B. (2015). Adjusted spectral matched filter for target detection in hyperspectral imagery. Remote Sensing, 7, 6611–6634.
Geng, X. (2005). Target detection and classification for hyperspectral image. Beijing: Institute of Remote Sensing Application, Chinese Academy of Science.
Harsanyi, J. C. (1993). Detection and classification of subpixel spectral signatures in hyperspectral image sequences. Ph.D., University of Maryland Baltimore County.
Kong, X. B., Shu, N., Tao, J. B., & Gong, G. (2011). A new spectral similarity measure based on multiple features integration. Spectroscopy and Spectral Analysis, 31(8), 2166–2170.
Kraut, S., & Scharf, L. L. (1999). The CFAR adaptive subspace detector is a scale-invariant GLRT. IEEE Transactions on Signal Processing, 47(9), 2538–2541.
Kruse, F. A., Kierein-Young, K. S., & Boardman, J. W. (1900). Mineral mapping at Cuprite, Nevada with a 63-channel imaging spectrometer. Photogrammetric Engineering and Remote Sensing, 56, 83–92.
Liu, C. H., & Li, P. (2009). Target detection in agriculture field by eigenvector reduction method of CEM. Computer & Computing Technologies in Agriculture LII, 317(2), 1–7.
Mailloux, R. J. (1995). Covariance matrix augmentation to produce adaptive array pattern troughs. Electronic Letter, 31, 771–772.
Robey, F. C., Fuhrmann, D. R., Kelly E. J., & Nitzberg, R. (1992). A CFAR adaptive matched filter detector. IEEE Transaction on Acoustic Speech and Signal Process, 22(1), 208–216.
Scholnik, D. P., & Coleman, J. O. (2000). Formulating wideband array—pattern optimizations. In Proceedings of IEEE international symposium on phased array systems and technology, Dana Point, CA.
Scholnik, D. P., & Coleman, J. O. (2001). Surdirectivity and SNR constrains in wideband array—pattern design. In Proceedings of IEEE international rader conference, Atlanta, GA.
Sun, Kang, Geng, Xiurui, & Ji, Luyan. (2014). A band selection approach for small target detection based on CEM. International Journal of Remote Sensing, 35(13), 4589–4600.
Wang, Y., Huang, S., Liu, D., & Wang, B. (2013a). A new band removed selection method for target detection in hyperspectral image. Journal of Optics, 42(3), 208–213.
Wang, K., Shu, N., Li, L., & Gong, Y. (2013b). Weighted hyperspectral image target detection algorithm based on ICA orthogonal subspace projection. Geomatics and Information Science of Wuhan University, 38(4), 440–444.
Yang, S., & Shi, Z. (2014). SparseCEM and SparseACE for hyperspectral image target detection. IEEE Geoscience and Remote Sensing Letters, 11(12), 2135–2139.
Acknowledgments
This work was supported by the National Natural Science Foundation of China under project No. 41174093 and No. 41574008.
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Wang, Y., Huang, S., Liu, D. et al. A Target Detection Method for Hyperspectral Imagery Based on Two-Time Detection. J Indian Soc Remote Sens 45, 239–246 (2017). https://doi.org/10.1007/s12524-016-0593-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12524-016-0593-2