Modeling data manifold geometry in hyperspectral imagery

A new approach to modeling the nonlinear structure of hyperspectral imagery is developed. The new approach extracts a coordinate system that preserves geodesic distances on the high-dimensional data manifold. Extant algorithms for modelling nonlinear structure such as ISOMAP have been developed for other applications and are globally optimal but are practical only for small data sets because of poor computational scaling. We develop an approach to improve the scaling of manifold algorithms to large remote sensing scenes and illustrate our approach with hyperspectral imagery. We also show that the manifold approach leads to significantly improved compression over a widely used classical method, the minimum noise fraction

[1]  John F. Mustard,et al.  Spectral unmixing , 2002, IEEE Signal Process. Mag..

[2]  Richard Barrett,et al.  Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods , 1994, Other Titles in Applied Mathematics.

[3]  Charles M. Bachmann,et al.  A credit assignment approach to fusing classifiers of multiseason hyperspectral imagery , 2003, IEEE Trans. Geosci. Remote. Sens..

[4]  John A. Antoniades,et al.  Effect of spectral resolution and number of wavelength bands in analysis of a hyperspectral data set using NRL's ORASIS algorithm , 1996, Optics + Photonics.

[5]  Charles M. Bachmann.  Improving the performance of classifiers in high-dimensional remote sensing applications: an adaptive resampling strategy for error-prone exemplars (ARESEPE) , 2003, IEEE Trans. Geosci. Remote. Sens..

[6]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[7]  Joshua B. Tenenbaum,et al.  The Isomap Algorithm and Topological Stability , 2002, Science.

[8]  George Karypis,et al.  Introduction to Parallel Computing , 1994 .

[9]  F. D. van der Meer,et al.  Iterative spectral unmixing (ISU) , 1999 .

[10]  Jincheng Gao,et al.  The effect of solar illumination angle and sensor view angle on observed patterns of spatial structure in tallgrass prairie , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[11]  D. Roberts,et al.  Green vegetation, nonphotosynthetic vegetation, and soils in AVIRIS data , 1993 .

[12]  Joseph W. Boardman,et al.  Analysis, understanding, and visualization of hyperspectral data as convex sets in n space , 1995, Defense, Security, and Sensing.

[13]  Thomas L. Ainsworth,et al.  Improvements to land-cover and invasive species mapping from hyperspectral imagery in the Virginia Coast reserve , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[14]  P. Switzer,et al.  A transformation for ordering multispectral data in terms of image quality with implications for noise removal , 1988 .

[15]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[16]  Chein-I Chang,et al.  Further investigations into the use of linear and nonlinear mixing models for hyperspectral image analysis , 2002, SPIE Defense + Commercial Sensing.

[17]  S. Sandmeier,et al.  The potential of hyperspectral bidirectional reflectance distribution function data for grass canopy characterization , 1999 .

[18]  Thomas L. Ainsworth,et al.  Exploiting manifold geometry in hyperspectral imagery , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Huafeng Xu,et al.  A self-organizing principle for learning nonlinear manifolds , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[20]  Charles M. Bachmann,et al.  Automatic classification of land cover on Smith Island, VA, using HyMAP imagery , 2002, IEEE Trans. Geosci. Remote. Sens..

[21]  J. S. Lee,et al.  Optimal polarimetric decomposition variables-non-linear dimensionality reduction , 2001, IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No.01CH37217).

[22]  John F. Mustard,et al.  Nonlinear spectral mixture modeling of lunar multispectral data: Implications for lateral transport , 1998 .