×

Spatial-spectral operator theoretic methods for hyperspectral image classification. (English) Zbl 1352.42044

The authors analyze data integration and fusion techniques for taking advantage of both spatial and spectral information in hyperspectral imagery. The techniques are based on outcomes of Laplace-type operators on data dependent graphs. The best results are observed when spatial and spectral information is used at all stages: in constructing the data adjacent matrix, and in building the new joint spatial-spectral Laplace operator on such a modified graph.

MSC:

42C99 Nontrigonometric harmonic analysis
94A08 Image processing (compression, reconstruction, etc.) in information and communication theory

Software:

LIBSVM
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput. 1396, 1373-1396 (2003) · Zbl 1085.68119 · doi:10.1162/089976603321780317
[2] Belkin, M., Niyogi, P.: Convergence of Laplacian eigenmaps. Statistics 19, 1-31 (2008) · Zbl 1157.68056
[3] Benedetto, J.J., Czaja, W., Dobrosotskaya, J., Doster, T., Duke, K., Gillis, D.: Integration of heterogeneous data for classification in hyperspectral satellite imagery. In: Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVIII, Proc. SPIE, vol. 839078, pp. 1-12. International Society for Optics and Photonics (2012)
[4] Benedetto, J.J., Czaja, W., Dobrosotskaya, J., Doster, T., Duke, K., Gillis, D.: Semi-supervised learning of heterogeneous data in remote sensing imagery. In: Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering X, Proc. SPIE, vol. 840104, pp. 1-12. International Society for Optics and Photonics (2012)
[5] Benedetto, J.J., Czaja, W., Ehler, M.: Wavelet packets for time frequency analysis of multispectral data. Int. J. Geomath. 4(2), 137-154 (2013) · Zbl 1279.42039 · doi:10.1007/s13137-013-0052-y
[6] Benedetto, J.J., Czaja, W., Ehler, M., Flake, C., Hirn, M.: Wavelet packets for multi- and hyper-spectral imagery. Proc. SPIE 753508, 1-11 (2010)
[7] Bernard, K., Tarabalka, Y., Angulo, J., Chanussot, J., Benediktsson, J.: Spectral-spatial classification of hyperspectral data based on a stochastic minimum spanning forest approach. IEEE Trans. Image Process. 21(4), 2008-2021 (2012) · Zbl 1381.62207 · doi:10.1109/TIP.2011.2175741
[8] Bishop, C.: Neural Networks for Pattern Recognition. Clarendon Press, Oxford (1995) · Zbl 0868.68096
[9] Bruzzone, L., Carlin, L.: A multilevel context-based system for classification of very high spatial resolution images. IEEE Trans. Geosci. Remote Sens. 44(9), 2587-2600 (2006) · Zbl 1142.34023 · doi:10.1109/TGRS.2006.875360
[10] Cahill, N.D., Chew, S.E., Wenger, P.S.: Spatial-spectral dimensionality reduction of hyperspectral imagery with partial knowledge of class labels. In: Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXI, Proc. SPIE. International Society for Optics and Photonics (2015)
[11] Cahill, N.D., Messinger, D.W., Czaja, W.: Schroedinger eigenmaps with nondiagonal potentials for spatial-spectral clustering of hyperspectral imagery. In: Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XX, Proc. SPIE, pp. 1-13. International Society for Optics and Photonics (2014)
[12] Camps-Valls, G., Bandos Marsheva, T.V., Zhou, D.: Semi-supervised graph-based hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 45(10), 3044-3054 (2007) · doi:10.1109/TGRS.2007.895416
[13] Camps-Valls, G., Gómez-Chova, L., Muñoz-Marí, J., Rojo-Álvarez, J.L., Martínez-Ramón, M.: Kernel-based framework for multitemporal and multisource remote sensing data classification and change detection. IEEE Trans. Geosci. Remote Sens. 46(6), 1822-1835 (2008) · doi:10.1109/TGRS.2008.916201
[14] Camps-Valls, G., Gomez-Chova, L., Munoz-Mari, J., Vila-Frances, J., Calpe-Maravilla, J.: Composite kernels for hyperspectral image classification. IEEE Geosci. Remote Sensing Lett. 3(1), 93-97 (2006) · doi:10.1109/LGRS.2005.857031
[15] Chang, C.C., Lin, C.J.: Libsvm: a library for support vector machines. http://www.csie.ntu.edu.tw/ cjlin/libsvm/ (2001). Accessed June 2013
[16] Cloninger, A., Czaja, W., Doster, T.: Operator analysis and diffusion based embeddings for heterogeneous data fusion. In: 3rd Place 2013 IEEE GRSS Data Fusion Contest: Fusion of Hyperspectral and LiDAR Data (2013) · Zbl 1409.68230
[17] Coifman, R., Lafon, S., Lee, A., Maggioni, M., Nadler, B., Warner, F., Zucker, S.: Geometric diffusions as a tool for harmonic analysis and structure definition of data: diffusion maps. Proc. Natl. Acad. Sci. USA 102(21), 7426-7431 (2005) · Zbl 1405.42043 · doi:10.1073/pnas.0500334102
[18] Coifman, R.R., Hirn, M.J.: Diffusion maps for changing data. Appl. Comput. Harmonic Anal. 36(1), 79-107 (2014) · Zbl 1302.62122 · doi:10.1016/j.acha.2013.03.001
[19] Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273-297 (1995) · Zbl 0831.68098
[20] Czaja, W., Ehler, M.: Schröedinger eigenmaps for the analysis of bio-medical data. IEEE Trans. Pattern Anal. Mach. Intell. 35(5), 1274-1280 (2013) · doi:10.1109/TPAMI.2012.270
[21] Donoho, D., Grimes, C.: Hessian eigenmaps: locally linear embedding techniques for high-dimensional data. Proc. Natl. Acad. Sci. 100(10), 5591-5596 (2003) · Zbl 1130.62337 · doi:10.1073/pnas.1031596100
[22] Doster, T.: Harmonic analysis inspired data fusion for applications in remote sensing. Ph.D. thesis, University of Maryland, College Park (2014) · Zbl 1381.62207
[23] Duke, K.: A study of the relationship between spectrum and geometry through fourier frames and Laplacian eigenmaps. Ph.D. thesis, University of Maryland, College Park (2012) · Zbl 1130.62337
[24] Fauvel, M., Benediktsson, J., Chanussot, J., Sveinsson, J.: Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles. IEEE Trans. Geosci. Remote Sens. 46(11), 3804-3814 (2008) · doi:10.1109/TGRS.2008.922034
[25] Fauvel, M., Chanussot, J., Benediktsson, J.: Kernel principal component analysis for the classification of hyperspectral remote sensing data over urban areas. EURASIP J. Adv. Signal Process 2009, 1-14 (2009) · Zbl 1130.62337
[26] Fauvel, M., Tarabalka, Y., Benediktsson, J., Chanussot, J., Tilton, J.: Advances in spectral-spatial classification of hyperspectral images. Proc. IEEE 101(3), 652-675 (2013) · doi:10.1109/JPROC.2012.2197589
[27] Gillis, D., Bowles, J.: Hyperspectral image segmentation using spatial-spectral graphs. In: SPIE Defense, Security, and Sensing, vol. 83901Q, pp. 1-11. International Society for Optics and Photonics (2012) · Zbl 1302.62122
[28] Goldberg, Y., Zakai, A., Kushnir, D., Ritov, Y.: Manifold learning: the price of normalization. J. Mach. Learn. Res. 9, 1909-1939 (2008) · Zbl 1225.68181
[29] Halevy, A.: Extensions of Laplacian eigenmaps for manifold learning. Ph.D Thesis, University of Maryland, College Park (2011) · Zbl 1279.42039
[30] Hou, B., Zhang, X., Ye, Q., Zheng, Y.: A novel method for hyperspectral image classification based on Laplacian eigenmap pixels distribution-flow. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 6(3), 1602-1618 (2013) · doi:10.1109/JSTARS.2013.2259470
[31] Hu, Y., Saber, E., Monteiro, S.T., Cahill, N.D., Messinger, D.W.: Classification of hyperspectral images based on conditional random fields. In: Image Processing: Machine Vision Applications VIII, Proc. SPIE. International Society for Optics and Photonics (2015)
[32] Kim, D., Finkel, L.: Hyperspectral image processing using locally linear embedding. In: Neural Engineering, 2003. Conference Proceedings. First International IEEE EMBS Conference on, pp. 316-319 (2003)
[33] Lee, M., Bruce, L., Prasad, S.: Concurrent spatial-spectral band grouping: Providing a spatial context for spectral dimensionality reduction. In: 3rd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), pp. 1-4 (2011)
[34] Ma, L., Crawford, M., Tian, J.: Generalised supervised local tangent space alignment for hyperspectral image classification. Electron. Lett. 46(7), 497-498 (2010) · doi:10.1049/el.2010.2613
[35] Manolakis, D., Marden, D., Shaw, G.: Hyperspectral image processing for automatic target detection applications. Lincoln Lab. J. 14(1), 79-116 (2003)
[36] Mohan, A., Sapiro, G., Bosch, E.: Spatially coherent nonlinear dimensionality reduction and segmentation of hyperspectral images. IEEE Geosci. Remote Sens. Lett. 4, 206-210 (2007) · doi:10.1109/LGRS.2006.888105
[37] Plaza, A., Martinez, P., Pérez, R., Plaza, J.: Spatial/spectral endmember extraction by multidimensional morphological operations. IEEE Trans. Geosci. Remote Sens. 40(9), 2025-2041 (2002) · doi:10.1109/TGRS.2002.802494
[38] Prasad, S., Bruce, L.: Limitations of principal components analysis for hyperspectral target recognition. IEEE Geosci. Remote Sens. Lett. 5, 625-629 (2008) · doi:10.1109/LGRS.2008.2001282
[39] Rajapakse, V., Czaja, W., Pommier, Y., Reinhold, W., Varma, S.: Predicting expression-related features of chromosomal domain organization with network-structured analysis of gene expression and chromosomal location. In: Proceedings of the ACM Conference on Bioinformatics, Computational Biology and Biomedicine, pp. 226-233 (2012)
[40] Roweis, S., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323-2326 (2000) · doi:10.1126/science.290.5500.2323
[41] Schaum, A., Stocker, A.: Hyperspectral change detection and supervised matched filtering based on covariance equalization. In: Proceedings of SPIE, vol. 5425, pp. 77-90 (2004)
[42] Schott, J.: Remote Sensing: The Image Chain Approach. Oxford University Press, New York (1997)
[43] Smith, M., Johnson, P., Adams, J.: Quantitative determination of mineral types and abundances from reflectance spectra using principal components analysis. In: Lunar and Planetary ScienceConference Proceedings, vol. 15, pp. 797-804 (1985)
[44] Tarabalka, Y., Benediktsson, J., Chanussot, J.: Spectral-spatial classification of hyperspectral imagery based on partitional clustering techniques. IEEE Trans. Geosci. Remote Sens. 47, 2973-2987 (2009) · doi:10.1109/TGRS.2009.2016214
[45] Tarabalka, Y., Benediktsson, J., Chanussot, J.: Spectral-spatial classification of hyperspectral imagery based on partitional clustering techniques. IEEE Trans. Geosci. Remote Sens. 47(8), 2973-2987 (2009) · doi:10.1109/TGRS.2009.2016214
[46] Tarabalka, Y., Tilton, J., Benediktsson, J., Chanussot, J.: A marker-based approach for the automated selection of a single segmentation from a hierarchical set of image segmentations. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 5(1), 262-272 (2012) · doi:10.1109/JSTARS.2011.2173466
[47] Thenkabail, P., Smith, R., De Pauw, E.: Hyperspectral vegetation indices and their relationships with agricultural crop characteristics. Remote Sens. Environ. 71(2), 158-182 (2000) · doi:10.1016/S0034-4257(99)00067-X
[48] Tilton, J., Tarabalka, Y., Montesano, P., Gofman, E.: Best merge region growing with integrated region object classification. IEEE Trans. Geosci. Remote Sens. 50, 4454-4467 (2012) · doi:10.1109/TGRS.2012.2190079
[49] Torgerson, W.S.: Multidimensional scaling: I. theory and method. Psychometrika 17(4), 401-419 (1952) · Zbl 0049.37603 · doi:10.1007/BF02288916
[50] Van Der Meer, F.: Analysis of spectral absorption features in hyperspectral imagery. Int. J. Appl. Earth Obs. Geoinform. 5(1), 55-68 (2004) · doi:10.1016/j.jag.2003.09.001
[51] Zhang, X., Chew, S.E., Xu, Z., Cahill, N.D.: Slic superpixels for efficient graph-based dimensionality reduction of hyperspectral imagery. In: IAlgorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXI, Proc. SPIE. International Society for Optics and Photonics (2015)
[52] Zhang, Z., Zha, H.: Principal manifolds and nonlinear dimension reduction via local tangent space alignment. SIAM J. Sci. Comput. 26, 313-338 (2002) · Zbl 1077.65042 · doi:10.1137/S1064827502419154
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.