Abstract
Orthogonal subspace projection (OSP) developed by Harsanyi and Chang (IEEE Transactions on Geoscience and Remote Sensing 32:779–785, 1994) (see Hyperspectral image: spectral techniques for detection and classification, Kluwer Academic Publishers, New York, 2003; Hyperspectral data processing: algorithm design and analysis, Wiley, Hoboken, 2013) has found its potential in many hyperspectral data exploitation applications. It works in two stages: an OSP-based projector to annihilate undesired signal sources in the first stage, to improve background suppression so as to increase target detectability, followed by a matched filter in the second stage, to extract the desired signal source for target enhancement. However, for OSP to be effective it assumes that the signal sources are provided a priori. As a result, OSP can only be used as a supervised algorithm. In many real-world applications, there are many unknown signal sources that can be revealed by hyperspectral imaging sensors. It is highly desirable to extend OSP to an unsupervised version, called unsupervised OSP (UOSP) developed by Wang et al. (Optical Engineering 41:1546–1557, 2002), where the signal sources used for OSP can be found in an unsupervised manner. An issue arising in UOSP is how to determine the number of such found unsupervised signal sources, which must be known in advance. This chapter further extends UOSP to progressive OSP (P-OSP) so that P-OSP can not only generate a growing set of new unknown signal sources one at a time progressively but can also determine the number of unknown signal sources to be generated while OSP processing is taking place. Since the unknown signal sources generated by P-OSP remain unchanged after they are generated, OSP should be able to take advantage of it without reprocessing these signal sources. This leads to a new development of a recursive version of OSP, called recursive hyperspectral sample processing of OSP (RHSP-OSP).
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
Chang, C.-I. 2013. Hyperspectral data processing: algorithm design and analysis. Hoboken: Wiley.
———. 2016. Real time progressive hyperspectral image processing: endmember finding and anomaly detection. New York: Springer.
Chang, C.-I., and Q. Du. 2004. Estimation of number of spectrally distinct signal sources in hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing 42(3): 608–619.
Chang, C.-I., and D. Heinz. 2000. Constrained subpixel detection for remotely sensed images. IEEE Transactions on Geoscience and Remote Sensing 38(3): 1144–1159.
Chang, C.-I., and J. Wang. 2008. Real-time implementation of field programmable gate arrays (FPGA) design in hyperspectral imagery. US Patent, number 7,366,326, April 29.
Chang, C.-I., S. Chakravarty, and C.-S. Lo. 2010a. Spectral feature probabilistic coding for hyperspectral signatures. IEEE Sensors Journal 10(3): 395–409.
Chang, C.-I., X. Jiao, Y. Du, and H.M. Chen. 2011b. Component-based unsupervised linear spectral mixture analysis for hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing 49(11): 4123–4137.
Chang, C.-I., W. Xiong, H.M. Chen, and J.W. Chai. 2011c. Maximum orthogonal subspace projection to estimating number of spectral signal sources for hyperspectral images. IEEE Journal of Selected Topics in Signal Processing 5(3): 504–520.
Chang, C.-I., W. Xiong, and C.H. Wen. 2014a. A theory of high order statistics-based virtual dimensionality for hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing 52(1): 188–208.
Chang, C.-I., S.Y. Chen, L. Zhao, and C.C. Wu. 2014b. Endmember-specified virtual dimensionality in hyperspectral imagery. In 2014 I.E. international geoscience and remote sensing symposium (IGARSS), Quebec, Canada, July 13–18.
Chen, S.Y., D. Paylor, and C.-I. Chang. 2014b. Anomaly discrimination in hyperspectral imagery. In Satellite data compression, communication and processing X (ST146), SPIE international symposium on SPIE sensing technology + applications, Baltimore, MD, 5–9 May.
Du, Q., N. Raksuntorn, N.H. Younan, and R.L. King. 2008b. Endmember extraction algorithms for hyperspectral image analysis. Applied Optics 47(28): F77–F84.
Harsanyi, J.C., and C.-I. Chang. 1994. Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approach. IEEE Transactions on Geoscience and Remote Sensing 32(4): 779–785.
Heinz, D., and C.-I. Chang. 2001. Fully constrained least squares linear mixture analysis for material quantification in hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing 39(3): 529–545.
Kuybeda, O., D. Malah, and M. Barzohar. 2007. Rank estimation and redundancy reduction of high-dimensional noisy signals with preservation of rare vectors. IEEE Transactions on Signal Processing 55(12): 5579–5592.
Leadbetter, M. 1987. Extremes and related properties of random sequences and processes. New York: Springer.
Poor, H.V. 1994. An introduction to detection and estimation theory, 2nd ed. New York: Springer.
Ren, H., and C.-I. Chang. 2003. Automatic spectral target recognition in hyperspectral imagery. IEEE Transactions on Aerospace and Electronic Systems 39(4): 1232–1249.
Song, M., Y. Li, C.-I. Chang, and L. Zhang. 2014a. Recursive orthogonal vector projection algorithm for linear spectral unmixing. In IEEE GRSS WHISPERS 2014 conference (workshop on hyperspectral image and signal processing: evolution in remote sensing, Lausanne, Switzerland, June 24–27.
Song, M., H.C. Li, C.-I. Chang, and Y. Li. 2014b. Gram-Schmidt orthogonal vector projection for hyperspectral unmixing. In 2014 I.E. international geoscience and remote sensing symposium (IGARSS), 2934–2937, Quebec, Canada, July 13–18.
Wang, C.M., C.C. Chen, S.-C. Yang, Y.-N. Chung, P.C. Chung, C.W. Yang, and C.-I. Chang. 2002. An unsupervised orthogonal subspace projection approach to MR image classification MR images for classification. Optical Engineering 41(7): 1546–1557.
Wang, L., F. Wei, D. Liu, and Q. Wang. 2013a. Fast implementation of maximum simplex volume-based endmember extraction in original hyperspectral data space. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 6(2): 516–521.
Wang, L., D. Liu, and Q. Wang. 2013b. Geometric method of fully constrained least squares linear spectral mixture analysis. IEEE Transactions on Geoscience and Remote Sensing 51(6): 3558–3566.
Yang, H., J. An, and C. Zhu. 2014. Subspace-projection-based geometric unmixing for material quantification in hyperspectral imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 7(6): 1966–1975.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Chang, CI. (2017). Recursive Hyperspectral Sample Processing of Orthogonal Subspace Projection. In: Real-Time Recursive Hyperspectral Sample and Band Processing. Springer, Cham. https://doi.org/10.1007/978-3-319-45171-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-45171-8_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-45170-1
Online ISBN: 978-3-319-45171-8
eBook Packages: EngineeringEngineering (R0)