×

On the use of small training sets for neural network-based characterization of mixed pixels in remotely sensed hyperspectral images. (English) Zbl 1175.68518

Summary: Neural network-based models involved in hyperspectral image spectra separation are considered. Focus is on how to select the most highly informative samples for effectively training the neural architecture. This issue is addressed here by several new algorithms for intelligent selection of training samples: (1) a border-training algorithm which selects training samples located in the vicinity of the hyperplanes that can optimally separate the classes; (2) a mixed-signature algorithm which selects the most spectrally mixed pixels in the hyperspectral data as training samples; and (3) a morphological-erosion algorithm which incorporates spatial information (via mathematical morphology concepts) to select spectrally mixed training samples located in spatially homogeneous regions. These algorithms, along with other standard techniques based on orthogonal projections and a simple Maximin-distance algorithm, are used to train a multi-layer perceptron, selected in this work as a representative neural architecture for spectral mixture analysis. Experimental results are provided using both a database of nonlinear mixed spectra with absolute ground truth and a set of real hyperspectral images, collected at different altitudes by the digital airborne imaging spectrometer and reflective optics system imaging spectrometer operating simultaneously at multiple spatial resolutions.

MSC:

68U10 Computing methodologies for image processing
68T05 Learning and adaptive systems in artificial intelligence
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Schowengerdt, R. A., Remote sensing: models and methods for image processing (1997), Academic Press: Academic Press New York
[2] Chang, C.-I., Hyperspectral imaging: techniques for spectral detection and classification (2003), Kluwer: Kluwer New York
[3] Du, Q.; Nekovei, R., Implementation of real-time constrained linear discriminant analysis to remote sensing image classification, Pattern Recognition, 38, 459-471 (2005) · Zbl 1079.68604
[4] Plaza, A.; Martinez, P.; Perez, R.; Plaza, J., A new approach to mixed píxel classification of hyperspectral imagery based on extended morphological profiles, Pattern Recognition, 37, 1097-1116 (2004)
[5] Du, Q.; Ren, H., Real-time constrained linear discriminant analysis to target detection and classification in hyperspectral imagery, Pattern Recognition, 36, 1-12 (2003) · Zbl 1010.68164
[6] Keshava, N.; Mustard, J. F., Spectral unmixing, IEEE Signal Processing Magazine, 19, 44-57 (2002)
[7] Adams, J. B.; Smith, M. O.; Johnson, P. E., Spectral mixture modeling: a new analysis of rock and soil types at the Viking Lander 1 site, Journal of Geophysical Research, 91, 8098-8112 (1986)
[8] Settle, J. J.; Drake, N. A., Linear mixing and the estimation of ground cover proportions, International Journal of Remote Sensing, 15, 2381-2392 (1993)
[9] Liu, W.; Wu, E. Y., Comparison of non-linear mixture models: sub-pixel classification, Remote Sensing of Environment, 18, 1976-2003 (2004)
[10] Wang, J.; Chang, C.-I., Applications of independent component analysis in endmember extraction and abundance quantification for hyperspectral imagery, IEEE Transactions on Geoscience and Remote Sensing, 44, 2601-2616 (2006)
[11] Nascimento, J. M.P.; Bioucas, J. M., Does independent component analysis play a role in unmixing hyperspectral data?, IEEE Transactions on Geoscience and Remote Sensing, 43, 175-187 (2005)
[12] Common, P., Independent component analysis: a new concept, Signal Processing, 36, 287-314 (1994)
[13] Wilkinson, G. G., Open questions in neurocomputing for earth observation, (Kanellopoulos, I.; Wilkinson, G. G.; Roli, F.; Austin, J., Neurocomputation in remote sensing data analysis (1999), Springer: Springer Berlin), 3-13
[14] Guilfoyle, K.; Althouse, M. L.; Chang, C.-I., A quantitative and comparative analysis of linear and nonlinear spectral mixture models using radial basis function neural networks, IEEE Transactions on Geoscience and Remote Sensing, 39, 2314-2318 (2001)
[15] Baraldi, A.; Binaghi, E.; Blonda, P.; Brivio, P. A.; Rampini, A., Comparison of the multilayer perceptron with neuro-fuzzy techniques in the estimation of cover class mixture in remotely sensed data, IEEE Transactions on Geoscience and Remote Sensing, 39, 994-1005 (2001)
[16] Bishop, C. M., Neural networks for pattern recognition (1995), Oxford University Press: Oxford University Press Oxford
[17] Huang, C.; Townshend, J. R.G., A stepwise regression tree for nonlinear approximation: applications to estimating subpixel land cover, International Journal of Remote Sensing, 24, 75-90 (2003)
[18] Zhuang, X.; Engel, B. A.; Lozano, D. F.; Fernández, R. B.; Johannsen, C. J., Optimization of training data required for neuro-classification, International Journal of Remote Sensing, 15, 3271-3277 (1999)
[19] Chi, M.; Bruzzone, L., A semilabeled-sample-driven bagging technique for ill-posed classification problems, IEEE Geoscience and Remote Sensing Letters, 2, 69-73 (2005)
[20] Lee, C.; Landgrebe, D. A., Decision boundary feature extraction for neural networks, IEEE Transactions on Neural Networks, 8, 75-83 (1997)
[21] Atkinson, P. M., Optimal ground-based sampling for remote-sensing investigations—estimating the regional mean, International Journal of Remote Sensing, 12, 559-567 (1991)
[22] Bruzzone, L.; Prieto, D. F., Unsupervised retraining of a maximum likelihood classifier for the analysis of multitemporal remote sensing images, IEEE Transactions on Geoscience and Remote Sensing, 39, 456-460 (2001)
[23] Chang, C.-I.; Du, Q., Estimation of number of spectrally distinct signal sources in hyperspectral imagery, IEEE Transactions on Geoscience and Remote Sensing, 42, 608-619 (2004)
[24] J.C. Harsanyi, W. Farrand, C.-I. Chang, Detection of subpixel spectral signatures in hyperspectral image sequences, in: Proceedings of the American Society on Photogrammetry and Remote Sensing, Reno, NV, 1994, pp. 236-247.; J.C. Harsanyi, W. Farrand, C.-I. Chang, Detection of subpixel spectral signatures in hyperspectral image sequences, in: Proceedings of the American Society on Photogrammetry and Remote Sensing, Reno, NV, 1994, pp. 236-247.
[25] J. Plaza, P. Martínez, R. Pérez, A. Plaza, Joint linear/nonlinear spectral unmixing of hyperspectral image data, in: Proceedings of IEEE International Geoscience and Remote Sensing Symposium, Barcelona, Spain, 2007, pp. 4037-4040.; J. Plaza, P. Martínez, R. Pérez, A. Plaza, Joint linear/nonlinear spectral unmixing of hyperspectral image data, in: Proceedings of IEEE International Geoscience and Remote Sensing Symposium, Barcelona, Spain, 2007, pp. 4037-4040.
[26] Foody, G. M.; Arora, M., Incorporating mixed pixels in the training, allocation and testing stages of supervised classifications, Pattern Recognition Letters, 17, 1389-1398 (1996)
[27] Brumbley, C.; Chang, C.-I., An unsupervised vector quantization-based target subspace projection approach to mixed pixel detection and classification in unknown background for remotely sensed imagery, Pattern Recognition, 32, 1161-1174 (1999)
[28] Tou, J. T.; González, R. C., Pattern Recognition Principles (1974), Addison-Wesley: Addison-Wesley Reading, MA, pp. 92-94
[29] Ren, H.; Chang, C.-I., Automatic spectral target recognition in hyperspectral imagery, IEEE Transactions on Aerospace and Electronic Systems, 39, 4, 1232-1249 (2003)
[30] Brumbley, C.; Chang, C.-I., An unsupervised vector quantization-based target subspace projection approach to mixed pixel detection and classification in unknown background for remotely sensed imagery, Pattern Recognition, 32, 1161-1174 (1999)
[31] Foody, G. M., The significance of border training patterns in classification by a feedforward neural network using backpropagation learning, International Journal of Remote Sensing, 20, 3549-3562 (1999)
[32] M.E. Winter, N-FINDR: an algorithm for fast autonomous spectral endmember determination in hyperspectral data, in: Proceedings of SPIE Image Spectrometry V, vol. 3753, 1999, pp. 266-277.; M.E. Winter, N-FINDR: an algorithm for fast autonomous spectral endmember determination in hyperspectral data, in: Proceedings of SPIE Image Spectrometry V, vol. 3753, 1999, pp. 266-277.
[33] Tadjudin, S.; Landgrebe, D. A., Covariance estimation with limited training samples, IEEE Transactions on Geoscience and Remote Sensing, 37, 2113-2118 (1999)
[34] Foody, G. M.; Mathur, A., Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification, Remote Sensing of Environment, 93, 107-117 (2004)
[35] Plaza, A.; Martínez, P.; Pérez, R.; Plaza, J., A quantitative and comparative analysis of endmember extraction algorithms from hyperspectral data, IEEE Transactions on Geoscience and Remote Sensing, 42, 650-663 (2004)
[36] Plaza, A.; Martínez, P.; Pérez, R.; Plaza, J., Spatial/spectral endmember extraction by multidimensional morphological operations, IEEE Transactions on Geoscience and Remote Sensing, 40, 2025-2041 (2002)
[37] Soille, P., Morphological Image Analysis: Principles and Applications (2003), Springer: Springer Berlin, Germany · Zbl 1012.68212
[38] Plaza, A.; Martínez, P.; Plaza, J.; Pérez, R., Dimensionality reduction and classification of hyperspectral image data using sequences of extended morphological transformations, IEEE Transactions on Geoscience and Remote Sensing, 43, 466-479 (2005)
[39] 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 (2000)
[40] Harsanyi, J.; Chang, C.-I., Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approach, IEEE Transactions on Geoscience and Remote Sensing, 32, 779-785 (1994)
[41] Pulido, F. J.; Díaz, M.; Hidalgo, S. J., Size structure and regeneration of Spanish holm oak quercus ilex forests and Dehesas: effects of agroforestry use on their long-term sustainability, Forest Ecology and Management, 146, 1-13 (2001)
[42] Müller, A.; Hausold, A.; Strobl, P., HySens-DAIS/ROSIS imaging spectrometers at DLR, (Proceedings of SPIE, vol. 5508 (2001)), 660-670
[43] A. Plaza, J. Le Moigne, N.S. Netanyahu, Morphological feature extraction for automatic registration of multispectral scenes, in: Proceedings of IEEE International Geoscience and Remote Sensing Symposium, Barcelona, Spain, 2007, pp. 421-424.; A. Plaza, J. Le Moigne, N.S. Netanyahu, Morphological feature extraction for automatic registration of multispectral scenes, in: Proceedings of IEEE International Geoscience and Remote Sensing Symposium, Barcelona, Spain, 2007, pp. 421-424.
[44] J. Plaza, A. Plaza, P. Martínez, R. Pérez, Nonlinear mixture models for analyzing laboratory simulated-forest hyperspectral data, in: Proceedings of SPIE, vol. 5508, 2003, pp. 660-670.; J. Plaza, A. Plaza, P. Martínez, R. Pérez, Nonlinear mixture models for analyzing laboratory simulated-forest hyperspectral data, in: Proceedings of SPIE, vol. 5508, 2003, pp. 660-670.
[45] J. Plaza, P. Martínez, A. Plaza, R. Perez, Quantifying the impact of spatial resolution on endmember extraction from hyperspectral imagery, in: Proceedings of third EARSeL Workshop on Imaging Spectroscopy, Herrsching, Germany, 2003, pp. 117-125.; J. Plaza, P. Martínez, A. Plaza, R. Perez, Quantifying the impact of spatial resolution on endmember extraction from hyperspectral imagery, in: Proceedings of third EARSeL Workshop on Imaging Spectroscopy, Herrsching, Germany, 2003, pp. 117-125.
[46] Carpenter, G. A.; Gopal, S.; Macomber, S.; Martens, S.; Woodcock, C. E., A neural network method for mixture estimation for vegetation mapping, Remote Sensing of Environment, 70, 138-152 (1999)
[47] J. Moreno, V. Caselles, J.A. Martínez-Lozano, J. Meliá, J. Sobrino, J.A. Calera, F. Montero, J.M. Cisneros, The measurements programme at Barrax, in: Proceedings of DAISEX Final Results Workshop, ESA SP-499, 2001, pp. 43-51.; J. Moreno, V. Caselles, J.A. Martínez-Lozano, J. Meliá, J. Sobrino, J.A. Calera, F. Montero, J.M. Cisneros, The measurements programme at Barrax, in: Proceedings of DAISEX Final Results Workshop, ESA SP-499, 2001, pp. 43-51.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.