Abstract
Hyperspectral classification techniques are widely used for detailed analysis of the earth surface. However, mixed pixels caused by the relatively low spatial resolution of the imaging system are the big burden for traditional pure-pixel-hypothesis based hard classification methods. To address this problem, a novel method, which jointly uses soft classification and spectral unmixing, is proposed in this paper. The confusion matrix is exploited to determine the endmember set for each class. Then the generated endmember is adopted for spectral unmixing. The fractional abundance of training samples, which is generated from spectral unmixing, is utilized to optimize soft multinomial logistic regression classifier. The result of the optimized classifier will result in a more accurate confusion matrix. Thus, this procedure is executed iteratively to achieve required performance. Experimental results on synthetic and real hyperspectral data sets demonstrate the superiority of the proposed method for hyperspectral image classification.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Tuia, D., Volpi, M., Copa, L., Kanevski, M., Munoz-Mari, J.: A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification. IEEE Journal of Selected Topics in Signal Processing 5(3), 606–617 (2011)
Plaza, A., Martin, G., Plaza, J., Zortea, M., Sanchez, S.: Recent Developments in Spectral Unmixing and Eendmember Extraction. In: Optical Remote Sensing-Advances in Signal Processing and Exploitation Techniques. Springer, New York (2010)
Villa, A., Chanussot, J., Benediktsson, J.A., Jutten, C.: Spectral Unmixing for the Classifica-tion of Hyperspectral Images at a Finer Spatial Resolution. IEEE Journal of Selected Topic in Signal Processing 5(3), 521–533 (2011)
Villa, A., Li, J., Plaza, A., Bioucas-Dias, J.M.: A New Semi-supervised Algorithm for Hyperspectral Image Classification based on Spectral Unmixing Concepts. In: 2011 3rd Workshop on Selected Topics in Signal Processing, Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS (2011)
Plaza, A., Martinez, P., Perez, R., Plaza, J.: A New Approach to Mixed Pixel Classification of Hyperspectral Imagery based on Extended Morphological Profiles. Pattern Recognition 37, 1097–1116 (2004)
Böhning, D.: Multinomial logistic regression algorithm. Annals of the Institute of Statistical Mathematics 44, 197–200 (1992)
Li, J., Bioucas-Dias, J., Plaza, A.: Semi-supervised Hyperspectral Image Segmentation Using Multinomial Logistic Regression with Active Learning. IEEE Transactions on Geo-science and Remote Sensing 48, 4085–4098 (2010)
Heinz, D., Chang, C.-I.: Fully Constrained Least Squares Linear Mixture Analysis for Material Quantification in Hyperspectral Imagery. IEEE Transactions on Geoscience and Remote Sensing 39, 529–545 (2001)
Li, J., Bioucas-Dias, J., Plaza, A.: Semi-supervised Hyperspectral Classification Using Soft Labels. In: IEEE GRSS Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2011 (2011)
Krishnapuram, B., Carin, L., Figueiredo, M., Hartemink, A.: Sparse Multinomial Logistic Regression: Fast algorithms and generalization bounds. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(6), 957–968 (2005)
USGS digital spectral library online, http://speclab.cr.usgs.gov
Meng, Q.J., Zhang, Y.N., Wei, W., Ren, Y.M., She, H.W.: Class-specific Artificial Immune Recognition Method for Hyperspectral Image Classification. In: 2012 IEEE 11th International Conference on Signal Processing (ICSP), pp. 851–855 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Meng, Q., Zhang, Y., Wei, W., Zhang, L. (2013). Spectral Unmixing for Hyperspectral Image Classification with an Adaptive Endmember Selection. In: Sun, C., Fang, F., Zhou, ZH., Yang, W., Liu, ZY. (eds) Intelligence Science and Big Data Engineering. IScIDE 2013. Lecture Notes in Computer Science, vol 8261. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-42057-3_46
Download citation
DOI: https://doi.org/10.1007/978-3-642-42057-3_46
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-42056-6
Online ISBN: 978-3-642-42057-3
eBook Packages: Computer ScienceComputer Science (R0)