[1] He Jun, Wang Qing, Li Zigang,. Enhanced hyperspectral imagery representationvia diffusion geometric coordinates [J]. Journal of Southeast University (English Edition), 2009, 25 (3): 351-355. [doi:10.3969/j.issn.1003-7985.2009.03.014]

Copy

Enhanced hyperspectral imagery representationvia diffusion geometric coordinates()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

25

Issue:

2009 3

Page:

351-355

Research Field:

Computer Science and Engineering

Publishing date:

2009-09-30

Info

Title:

Enhanced hyperspectral imagery representationvia diffusion geometric coordinates

Author(s):

He Jun;  Wang Qing;  Li Zigang

School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China

Keywords:

hyperspectral imagery;  diffusion geometric coordinate;  diffusion map;  nonlinear dimension reduction

PACS:

TP391

DOI:

10.3969/j.issn.1003-7985.2009.03.014

Abstract:

The concise and informative representation of hyperspectral imagery is achieved via the introduced diffusion geometric coordinates derived from nonlinear dimension reduction maps — diffusion maps.The huge-volume high-dimensional spectral measurements are organized by the affinity graph where each node in this graph only connects to its local neighbors and each edge in this graph represents local similarity information.By normalizing the affinity graph appropriately, the diffusion operator of the underlying hyperspectral imagery is well-defined, which means that the Markov random walk can be simulated on the hyperspectral imagery.Therefore, the diffusion geometric coordinates, derived from the eigenfunctions and the associated eigenvalues of the diffusion operator, can capture the intrinsic geometric information of the hyperspectral imagery well, which gives more enhanced representation results than traditional linear methods, such as principal component analysis based methods.For large-scale full scene hyperspectral imagery, by exploiting the backbone approach, the computation complexity and the memory requirements are acceptable.Experiments also show that selecting suitable symmetrization normalization techniques while forming the diffusion operator is important to hyperspectral imagery representation.

References:

[1] Bachmann C M, Ainsworth T L, Fusina R A.Exploiting manifold geometry in hyperspectral imagery [J].IEEE Trans Geosci Remote Sens, 2005, 43(3):441-454.
[2] Bachmann C M, Ainsworth T L, Fusina R A.Improved manifold coordinate representations of large-scale hyperspectral scenes [J].IEEE Trans Geosci Remote Sens, 2006, 44(10):2786-2803.
[3] Mohan A, Sapiro G, Bosch E.Spatially coherent nonlinear dimensionality reduction and segmentation of hyperspectral images [J].IEEE Geosci Remote Sens Lett, 2007, 4(2):206-210.
[4] Green A A, Berman M, Switzer P, et al.A transformation for ordering multispectral data in terms of image quality with implications for noise removal [J].IEEE Trans Geosci Remote Sens, 1988, 26(1):65-74.
[5] Tenenbaum J B, Silva V, Langford J C.A global geometric framework for nonlinear dimensionality reduction [J].Science, 2000, 290(5500):2319-2323.
[6] Roweis S T, Saul L K.Nonlinear dimensionality reduction by locally linear embedding [J].Science, 2000, 290(5500):2323-2327.
[7] Belkin M, Niyogi P.Laplacian eigenmaps for dimensionality reduction and data representation [J].Neural Comput, 2003, 15(6):1373-1396.
[8] Coifman R R, Lafon S, Lee A B, et al.Geometric diffusions as a tool for harmonic analysis and structure definition of data:diffusion maps [J].Proc of the National Academy of Sciences, 2005, 102(21):7426-7431.
[9] Lafon S.Diffusion maps and geometric harmonics [D].New Haven:Department of Mathematics of Yale University, 2004.
[10] Hein M, Audibert J Y, Luxburg U V.From graphs to manifolds-weak and strong pointwise consistency of graph Laplacians [C]//Proc of the 18th Conference on Learning Theory (COLT).Bertinoro, 2005:470-485.
[11] Coifman R R, Lafon S.Diffusion maps [J].Appl Comput Harmon Anal, 2006, 21(1):5-30.
[12] Arya S, Mount D M, Netanyahu N S, et al.An optimal algorithm for approximate nearest neighbor searching [J].J ACM, 1998, 45(6):891-923.
[13] Saul L K, Roweis S T.Think globally, fit locally:unsupervised learning of low dimensional manifolds [J].J Mach Learn Res, 2003, 4(2):119-155.
[14] AVIRIS [EB/OL].(1997)[2008-05-30].http://aviris.jpl.nasa.gov/html/aviris.instrument.html.
[15] Opticks [EB/OL].(2007)[2008-06-30].https://opticks.ballforge.net.
[16] Coifman R R, Maggioni M.Diffusion wavelets [J].Appl Comput Harmon Anal, 2006, 21(1):53-94.

Memo

Memo:

Biographies: He Jun(1978—), male, graduate;Wang Qing(corresponding author), male, doctor, professor, wq_-seu@seu.edu.cn.
Foundation item: The National Key Technologies R& D Program during the 11th Five-Year Plan Period(No.2006BAB15B01).
Citation: He Jun, Wang Qing, Li Zigang.Enhanced hyperspectral imagery representation via diffusion geometric coordinates[J].Journal of Southeast University(English Edition), 2009, 25(3):351-355.

Common functions