Abstract
In this work, a novel target detector for hyperspectral imagery is developed. The detector is independent on the unknown covariance matrix, behaves well in large dimensions, distributional free, invariant to atmospheric effects, and does not require a background dictionary to be constructed. Based on a modification of the robust principal component analysis (RPCA), a given hyperspectral image (HSI) is regarded as being made up of the sum of a low-rank background HSI and a sparse target HSI that contains the targets based on a pre-learned target dictionary specified by the user. The sparse component is directly used for the detection, that is, the targets are simply detected at the non-zero entries of the sparse target HSI. Hence, a novel target detector is developed, which is simply a sparse HSI generated automatically from the original HSI, but containing only the targets with the background is suppressed. The detector is evaluated on real experiments, and the results of which demonstrate its effectiveness for hyperspectral target detection especially when the targets are well matched to the surroundings.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A natural suggestion could be that the rank of \(\mathbf {L}\) usually has a physical meaning (e.g., number of endmembers in background), and thus, why not to minimize the latter two terms in Eq. (15.2) with the constraint that the rank of \(\mathbf {L}\) should not be larger than a fixed value d? That is,
$$ \underset{\mathbf {L}, \mathbf {C}}{\mathrm {min}} \, \left\{ \lambda \,\left\| \mathbf {C}\right\| _{2,1} + \left\| \mathbf {D} - \mathbf {L} - \left( \mathbf {A}_t \mathbf {C}\right) ^T\right\| _F^2 \right\} \,, ~~s.t.~~ \mathrm {rank}(\mathbf {L}) \le d. $$In our opinion, assuming that the number of endmembers in background is known exactly will be a strong assumption and our work will be less general as a result. One can assume d to be some upper bound, in which case, the suggested formulation is a possible one. However, solving such a problem (with a hard constraint that the rank should not exceed some bound) is in general a NP-hard problem, unless there happens to be some special form in the objective which allows for a tractable solution. Thus, we adopt the soft constraint form with the nuclear norm as a proxy for the rank of \(\mathbf {L}\); this is an approximation commonly done in the field and is found to give good solutions in many problems empirically.
- 2.
- 3.
The MATLAB code of the proposed detector and experiments is available upon request. Please feel free to contact Ahmad W. Bitar.
- 4.
We thank Dr. Gregg A. Swayze from the United States Geological Survey (USGS) who has suggested us to evaluate our model (15.2) on the distinction between alunite and kaolinite minerals.
- 5.
References
Shaw G, Manolakis D (2002) Signal processing for hyperspectral image exploitation. IEEE Signal Process Mag 19(1):12–16
Manolakis D, Marden D, Shaw G (2003) Hyperspectral image processing for automatic target detection applications. Linc Lab J 14(1):79–116
Manolakis DG, Lockwood RB, Cooley TW (2016) Hyperspectral imaging remote sensing: physics, sensors, and algorithms. Cambridge University Press
Zhang L, Zhang Q, Du B, Huang X, Tang YY, Tao D (2018) Simultaneous spectral-spatial feature selection and extraction for hyperspectral images. IEEE Trans Cybern 48(1):16–28
Zhang L, Zhang Q, Zhang L, Tao D, Huang X, Du B (2015) Ensemble manifold regularized sparse low-rank approximation for multiview feature embedding. Pattern Recognit48(10):3102 – 3112 (Discriminative feature learning from big data for visual recognition)
Bioucas-Dias JM, Plaza A, Camps-Valls G, Scheunders P, Nasrabadi N, Chanussot J (2013) Hyperspectral remote sensing data analysis and future challenges. IEEE Geosci Remote Sens Mag 1(2):6–36
Plaza A, Benediktsson JA, Boardman JW, Brazile J, Bruzzone L, Camps-Valls G, Chanussot J, Fauvel M, Gamba P, Gualtieri A, Marconcini M, Tilton JC, Trianni (2009) Recent advances in techniques for hyperspectral image processing. Remote Sens Environ 113:S110–S122, (Imaging spectroscopy special issue)
Du Q, Zhang L, Zhang B, Tong X, Du P, Chanussot J (2013) Foreword to the special issue on hyperspectral remote sensing: theory, methods, and applications. IEEE J Sel Top Appl Earth Obs Remote Sens 6(2):459–465
Gader PD, Chanussot J (2021) Understanding hyperspectral image and signal processing, Wiley
Dalla Mura M, Benediktsson JA, Chanussot J, Bruzzone L (2011) The evolution of the morphological profile: from panchromatic to hyperspectral images, Springer, Berlin, Heidelberg, pp 123–146
Prasad S, Bruce LM, Chanussot J (2011) Optical remote sensing: advances in signal processing and exploitation techniques. Augmented vision and reality. Springer, Heidelberg
Chanussot J, Collet C, Chehdi K (2009) Multivariate image processing, augmented vision and reality. STE Ltd, UK and Wiley, USA
Pons JMF (2014) Robust target detection for hyperspectral imaging. PhD thesis, CentraleSupélec
Manolakis D, Lockwood R, Cooley T, Jacobson J (2009) Is there a best hyperspectral detection algorithm? In: Proceeding of SPIE 7334, algorithms and technologies for multispectral, hyperspectral, and ultraspectral imagery XV, 733402, 27 April 2009
Villa A, Chanussot J, Benediktsson JA, Jutten C (2011) Unsupervised classification and spectral unmixing for sub-pixel labelling. In: IEEE International geoscience and remote sensing symposium, July, 71–74
Yokoya N, Chanussot J, Iwasaki A (2014) Nonlinear unmixing of hyperspectral data using semi-nonnegative matrix factorization. IEEE Trans Geosci Remote Sens 52(2):1430–1437
Villa A, Chanussot J, Benediktsson JA, Jutten C (2011) Spectral unmixing for the classification of hyperspectral images at a finer spatial resolution. IEEE J Sel Top Signal Process 5(3):521–533
Licciardi GA, Villa A, Khan MM, Chanussot J (2012) Image fusion and spectral unmixing of hyperspectral images for spatial improvement of classification maps. In: IEEE International and geosciencing remote sensing symposium, July, pp 7290–7293
Patel NK, Patnaik C, Dutta S, Shekh AM, Dave AJ (2001) Study of crop growth parameters using airborne imaging spectrometer data. Int J Remote Sens 22(12):2401–2411
Datt B, McVicar TR, van Niel TG, Jupp DLB, Pearlman JS (2003) Preprocessing EO-1 Hyperion hyperspectral data to support the application of agricultural indexes. IEEE Trans Geosci Remote Sens 41:1246–1259
Hörig B, Kühn F, Oschütz F, Lehmann F (2001) HyMap hyperspectral remote sensing to detect hydrocarbons. Int J Remote Sens 22:1413–1422
Manolakis D, Shaw G (2002) Detection algorithms for hyperspectral imaging applications. Signal Process Mag IEEE 19(1):29–43
Stein DWJ, Beaven SG, Hoff LE, Winter EM, Schaum AP, Stocker AD (2002) Anomaly detection from hyperspectral imagery. IEEE Signal Process Mag 19(1):58–69
Eismann MT, Stocker AD, Nasrabadi NM (2009) Automated hyperspectral cueing for civilian search and rescue. Proc IEEE 97(6):1031–1055
Manolakis D, Truslow E, Pieper M, Cooley T, Brueggeman M (2014) Detection algorithms in hyperspectral imaging systems: an overview of practical algorithms. IEEE Signal Process Mag 31(1):24–33
Frontera-Pons J, Pascal F, Ovarlez J-P (2017) Adaptive nonzero-mean Gaussian detection. IEEE Trans Geosci Remote Sens 55(2):1117–1124
Frontera-Pons J, Veganzones MA, Pascal F, Ovarlez J-P (2016) Hyperspectral anomaly detectors using robust estimators. IEEE J Sel Top Appl Earth Obs Remote Sens 9(2):720–731
Frontera-Pons J, Ovarlez J-P, Pascal F (2017) Robust ANMF detection in noncentered impulsive background. IEEE Signal Process Lett 24(12):1891–1895
Frontera-Pons J, Veganzones MA, Velasco-Forero S, Pascal F, Ovarlez JP, Chanussot J (2014) Robust anomaly detection in hyperspectral imaging. In: IEEE geoscience and remote sensing symposium, July, pp 4604–4607
Cavalli RM, Licciardi GA, Chanussot J (2013) Detection of anomalies produced by buried archaeological structures using nonlinear principal component analysis applied to airborne hyperspectral image. IEEE J Sel Top Appl Earth Obs Remote Sens 6(2):659–669
Manolakis D, Shaw G, Keshava N (2000) Comparative analysis of hyperspectral adaptive matched filter detectors. In: Proceedings of SPIE 4049, algorithms for multispectral, hyperspectral, and ultraspectral imagery VI, vol 2
Nasrabadi NM (2008) Regularized spectral matched filter for target recognition in hyperspectral imagery. IEEE Signal Process Lett 15:317–320
Kraut S, Scharf LL (1999) The CFAR adaptive subspace detector is a scale-invariant GLRT. On Signal Process, IEEE Trans 47(9):2538–2541
Kelly EJ (1986) An adaptive detection algorithm. IEEE Trans Aerosp Electron Syst 23(1):115–127
Ledoit O, Wolf M (2004) A well-conditioned estimator for large-dimensional covariance matrices. J Multivar Anal 88(2):365–411
Ledoit O, Wolf M, (2003) Honey, I shrunk the sample covariance matrix. UPF Economics and Business Working Paper, no. 691
Bitar AW, Ovarlez J-P, Cheong L-F (2017) Sparsity-based cholesky factorization and its application to hyperspectral anomaly detection. In: IEEE workshop on computational advances in multi-sensor adaptive processing (CAMSAP-17). Curaçao, Dutch Antilles
Chen Y, Wiesel A, Hero AO (2010) Robust shrinkage estimation of high-dimensional covariance matrices. In: IEEE Sensor Array and Multichannel Signal Processing Workshop, OCt, 189–192
Pascal F, Chitour Y (2014) Shrinkage covariance matrix estimator applied to stap detection. In: IEEE workshop on statistical signal processing (SSP), June, 324–327
Pascal F, Chitour Y, Quek Y (2014) Generalized robust shrinkage estimator and its application to stap detection problem. IEEE Trans Signal Process 62(21):5640–5651
Healey G, Slater D (1999) Models and methods for automated material identification in hyperspectral imagery acquired under unknown illumination and atmospheric conditions. IEEE Trans Geosci Remote Sens 37(6):2706–2717
Thai B, Healey G (2002) Invariant subpixel material detection in hyperspectral imagery. IEEE Trans Geosci Remote Sens 40(3):599–608
Wright J, Yang AY, Ganesh A, Sastry SS, Ma Y (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31(2):210–227
Basri R, Jacobs DW (2003) Lambertian reflectance and linear subspaces. IEEE Trans Pattern Anal Mach Intell 25(2):218–233
Pillai JK, Patel VM, Chellappa R (2009) Sparsity inspired selection and recognition of iris images. In: 2009 IEEE 3rd international conference on biometrics: theory, applications, and systems, Sept, pp 1–6
Hang X, Wu F-X (2009) Sparse representation for classification of tumors using gene expression data. J Biomed Biotechnol 6
Guo Z, Wittman T, Osher S (2009) L1 unmixing and its application to hyperspectral image enhancement
Bioucas-Dias JM, Plaza A, Dobigeon N, Parente M, Du Q, Gader P, Chanussot J (2012) Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approaches. IEEE J Sel Top Appl Earth Obs Remote Sens 5(2):354–379
Chen Y, Nasrabadi NM, Tran TD (2011) Sparse representation for target detection in hyperspectral imagery. IEEE J Sel Top Signal Process 5(3):629–640
Zhang Y, Du B, Zhang L (2015) A sparse representation-based binary hypothesis model for target detection in hyperspectral images. IEEE Trans Geosci Remote Sens 53(3):1346–1354
Bitar AW, Cheong L, Ovarlez J (2018) Target and background separation in hyperspectral imagery for automatic target detection. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 1598–1602
Bitar AW, Cheong L, Ovarlez J (2019) Sparse and low-rank matrix decomposition for automatic target detection in hyperspectral imagery. IEEE Trans Geosci Remote Sens 57(8):5239–5251
Candès EJ, Li X, Ma Y, Wright J (2011) Robust principal component analysis? J ACM 58(3):11:1–11:37
Wright J, Arvind G, Shankar R, Yigang P, Ma Y (2009) Robust principal component analysis: exact recovery of corrupted low-rank matrices via convex optimization. In: Bengio Y, Schuurmans D, Lafferty JD, Williams CKI, Culotta A (eds) Advances in neural information processing systems, vol 22. Curran Associates, Inc., pp 2080–2088
Chen S-Y, Yang S, Kalpakis K, Chang C (2013) Low-rank decomposition-based anomaly detection. In: Proceedings of SPIE 8743 algorithms and technologies for multispectral, hyperspectral, and ultraspectral imagery XIX, vol 8743, pp 1–7
Zhang Y, Du B, Zhang L, Wang S (2016) A low-rank and sparse matrix decomposition-based Mahalanobis distance method for hyperspectral anomaly detection. IEEE Trans Geosci Remote Sens 54(3):1376–1389
Xu Y, Wu Z, Li J, Plaza A, Wei Z (2016) Anomaly detection in hyperspectral images based on low-rank and sparse representation. IEEE Trans Geosci Remote Sens 54(4):1990–2000
Xu Y, Wu Z, Chanussot J, Wei Z (2018) Joint reconstruction and anomaly detection from compressive hyperspectral images using mahalanobis distance-regularized tensor RPCA. IEEE Trans Geosci Remote Sens 56(5):2919–2930
Xu Y, Wu Z, Chanussot J, Dalla Mura M, Bertozzi AL, Wei Z (2018) Low-rank decomposition and total variation regularization of hyperspectral video sequences. IEEE Trans Geosci Remote Sens 56(3):1680–1694
Bitar AW, Cheong L, Ovarlez J (2017) Simultaneous sparsity-based binary hypothesis model for real hyperspectral target detection. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 4616–4620
Veganzones MA, Simões M, Licciardi G, Yokoya N, Bioucas-Dias JM, Chanussot J (2016) Hyperspectral super-resolution of locally low rank images from complementary multisource data. IEEE Trans Image Process 25(1):274–288
Liu G, Lin Z, Yan S, Sun J, Yu Y, Ma Y (2013) Robust recovery of subspace structures by low-rank representation. IEEE Trans Pattern Anal Mach Intell 35(1):171–184
Zhou Z, Li X, Wright J, Candés E, Ma Y (2010) Stable principal component pursuit. In: 2010 IEEE International symposium on information theory, pp 1518–1522
Chen Z, Ellis DPW (2013) Speech enhancement by sparse, low-rank, and dictionary spectrogram decomposition. In: IEEE Workshop on applications of signal processing to audio and acoustics Oct, 1–4
Sun P, Qin J (2016) Low-rank and sparsity analysis applied to speech enhancement via online estimated dictionary. IEEE Signal Process Lett 23(12):1862–1866
Cai J-F, Candès EJ, Shen Z (2010) A singular value thresholding algorithm for matrix completion. SIAM J Optim 20(4):1956–1982
Candes EJ, Recht B, Exact low-rank matrix completion via convex optimization. In: 2008 46th Annual allerton conference on communication, control, and computing, Sept, pp 806–812
Lewis AS (2003) The mathematics of eigenvalue optimization. Math Program 97(1):155–176
Watson GA (1992) Characterization of the subdifferential of some matrix norms. Linear Algebr Its Appl 170:33–45
Boyd Stephen, Parikh Neal, Chu Eric, Peleato Borja, Eckstein Jonathan (2011) Distributed optimization and statistical learning via the alternating direction method of multipliers. Found Trends Mach Learn 3(1):1–122
Yang Junfeng, Yin Wotao, Zhang Yin, Wang Yilun (2009) A fast algorithm for edge-preserving variational multichannel image restoration. SIAM J Imaging Sci 2(2):569–592
Swayze GA, Clark RN, Goetz AFH, Livo KE, Breit GN, Kruse FA, Sutley SJ, Snee LW, Lowers HA, Post JL, Stoffregen RE, Ashley RP (2014) Mapping advanced argillic alteration at cuprite, nevada, using imaging spectroscopy. Econ Geol 109(5):1179
Airbone Visible/Infrared Imaging Spectrometer. https://aviris.jpl.nasa.gov
Swayze GA, Clark RN, Goetz AFH, Chrien TG, Gorelick NS (2003) Effects of spectrometer band pass, sampling, and signal-to-noise ratio on spectral identification using the tetracorder algorithm. J Geophys Res: Planets 108(E9):5105
Clark RN, Swayze GA, Livo KE, Kokaly RF, Sutley SJ, Dalton JB, McDougal RR, Gent CA, Imaging spectroscopy: earth and planetary remote sensing with the usgs tetracorder and expert systems. J Geophys Res: Planets 108(E12)
Berk A, Bernstein L, Robertson D (1989) MODTRAN: a moderate resolution model for LOWTRAN 7. Tech. Rep. GL-TR-90-0122, Geophysics Laboratory, Bedford, MA
Clark RN, Swayze GA, Gallagher AJ, King TVV, Calvin WM (1993) The U.S. geological survey, digital spectral library: version 1: 0.2 to 3.0 micros. U.S. Geological Survey, Open file report
Baldridge AM, Hook SJ, Grove CI, Rivera G (2009) The ASTER Spectral Library Version 2.0. Remote Sens Environ 113:711–715
Tibshirani R (1996) Regression shrinkage and selection via the lasso. J R Stat Soc Ser B (Methodol) 58(1):267–288
Efron B, Hastie T, Johnstone I, Tibshirani R (2004) Least angle regression. Ann Stat 32(2):407–451
Shevade SK, Keerthi SS (2003) A simple and efficient algorithm for gene selection using sparse logistic regression. Bioinformatics 19(17):2246–2253
Amir B, Marc T (2009) A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J Img Sci 2(1):183–202
Wright SJ, Nowak RD, Figueiredo MAT (2009) Sparse reconstruction by separable approximation. IEEE Trans Signal Process 57(7):2479–2493
Ye Jieping, Liu Jun (2012) Sparse methods for biomedical data. SIGKDD Explor Newsl 14(1):4–15
Candès Emmanuel J, Wakin Michael B, Boyd Stephen P (2008) Enhancing sparsity by reweighted \(l_1\) minimization. J Fourier Anal Appl 14(5):877–905
Zhang Tong (2010) Analysis of multi-stage convex relaxation for sparse regularization. J Mach Learn Res 11:1081–1107
Zhang T (2013) Multi-stage convex relaxation for feature selection Bernoulli 19(5B):2277–2293
Foucart S, Lai MJ (2009) Sparsest solutions of underdetermined linear systems via \(l_q\)-minimization for \(0< q <1\). Appl Comput Harmon Anal 26(3):395–407
Fan J, Li R (2001) Variable selection via nonconcave penalized likelihood and its oracle properties. J Am Stat Assoc 96(456):1348–1360
Candès E, Wakin MB, Boyd SP (2008) Enhancing sparsity by reweighted l1 minimization. J Fourier Anal Appl 14(5):877–905
Zhang CH (2010) Nearly unbiased variable selection under minimax concave penalty. Ann Statist 38(2):894–942
Geman D, Yang C (1995) Nonlinear image recovery with half-quadratic regularization. IEEE Trans Image Process 4(7)932–946, Jul
Trzasko J, Manduca A (2009) Relaxed conditions for sparse signal recovery with general concave priors. IEEE Trans Signal Process 57(11):4347–4354
Gong P, Ye J, Zhang C (2012) Multi-stage multi-task feature learning. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ (eds) Advances in neural information processing systems vol 25. Curran Associates, Inc., pp 1988–1996
Acknowledgements
The authors would greatly thank Dr. Gregg A. Swayze from the United States Geological Survey (USGS) for his time in providing them helpful remarks about the cuprite data and especially on the buddingtonite, alunite, and kaolinite minerals. They would also like to thank the handling editors (Prof. Saurabh Prasad and Prof. Jocelyn Chanussot) and some other anonymous reviewers for the careful reading and helpful remarks/suggestions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Bitar, A.W., Ovarlez, JP., Cheong, LF., Chehab, A. (2020). Automatic Target Detection for Sparse Hyperspectral Images. In: Prasad, S., Chanussot, J. (eds) Hyperspectral Image Analysis. Advances in Computer Vision and Pattern Recognition. Springer, Cham. https://doi.org/10.1007/978-3-030-38617-7_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-38617-7_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-38616-0
Online ISBN: 978-3-030-38617-7
eBook Packages: Computer ScienceComputer Science (R0)