Abstract
Due to the limited resolution of hyperspectral sensors, anomalous targets expressed with subpixels are often mixed with nonhomogeneous backgrounds. This fact makes anomalies difficult to be distinguished from the surrounding background. From this perspective, we propose a novel hyperspectral anomaly detection (AD) algorithm based on low-rank & sparse matrix decomposition (LRaSMD) and support vector machine (SVM). First, based on the LRaSMD technique, the Go decomposition (GoDec) model is utilized to decompose the original image into three components: background, anomalies and noise. In this way, the robust background can be obtained. Subsequently, a clustering algorithm is employed to pick some obvious anomalies. Accordingly, we use both samples of background and anomaly to train an SVM model. The original dataset is sent into the SVM model and both anomalous components and background components can be classified. Experiments on a synthetic hyperspectral image validate the performance of the proposed method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Landgrebe, D.: Hyperspectral image data analysis. IEEE Sig. Process. Mag. 19, 17–28 (2002)
Reed, I.S., Yu, X.: Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution. IEEE Trans. Acoust. Speech Sig. Process. 38, 1760–1770 (1990)
Schaum, A.: Joint subspace detection of hyperspectral targets. In: Proceedings of the IEEE Aerospace Conference, vol. 3, pp. 1824 (2004)
Molero, J.M., Garzón, E.M., García, I., Plaza, A.: Analysis and optimizations of global and local versions of the RX algorithm for anomaly detection in hyperspectral data. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 6(2), 801–814 (2013)
Sun, W., Liu, C., Li, J., Lai, Y.M., Li, W.: Low-rank and sparse matrix decomposition-based anomaly detection for hyperspectral imagery. J. Appl. Remote Sens. 8, 083641 (2014)
Zhang, Y., Du, B., Zhang, L., Wang, S.: A low-rank and sparse matrix decomposition-based mahalanobis distance method for hyperspectral anomaly detection. IEEE Trans. Geosci. Remote Sens. 54, 1376–1389 (2016)
Candès, E.J., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? ACM 3, 11 (2011)
Liu, G., Lin, Z., Yu, Y.: Robust subspace segmentation by low-rank representation. In: Proceedings of the 27th International Conference on Machine Learning (ICML), pp. 663–670 (2010)
Zhou, T.; Tao, D.: GoDec: Randomized low-rank & sparse matrix decomposition in noisy case. In: Proceedings of the International Conference Machine Learning, pp. 33–40 (2011)
Melgani, F., Bruzzone, L.: Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans. Geosci. Remote Sens. 42(8), 1778–1790 (2004)
Stefanou, M.S., Kerekes, J.P.: A method for assessing spectral image utility. IEEE Trans. Geosci. Remote Sens. 47(6), 1698–1706 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Song, S. et al. (2020). Low-Rank & Sparse Matrix Decomposition and Support Vector Machine for Hyperspectral Anomaly Detection. In: McDaniel, T., Berretti, S., Curcio, I., Basu, A. (eds) Smart Multimedia. ICSM 2019. Lecture Notes in Computer Science(), vol 12015. Springer, Cham. https://doi.org/10.1007/978-3-030-54407-2_26
Download citation
DOI: https://doi.org/10.1007/978-3-030-54407-2_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-54406-5
Online ISBN: 978-3-030-54407-2
eBook Packages: Computer ScienceComputer Science (R0)