Korean Journal of Remote Sensing (대한원격탐사학회지)

Korean Society of Remote Sensing (대한원격탐사학회)
권호 표지
DOI QR코드

DOI QR Code

Integrating Spatial Proximity with Manifold Learning for Hyperspectral Data

  • Kim, Won-Kook (Laboratory for Applications of Remote Sensing, Purdue University) ;
  • Crawford, Melba M. (Laboratory for Applications of Remote Sensing, Purdue University) ;
  • Lee, Sang-Hoon (Department of Industrial Engineering, Kyungwon University)
  • Received : 2010.12.10
  • Accepted : 2010.12.23
  • Published : 2010.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

High spectral resolution of hyperspectral data enables analysis of complex natural phenomena that is reflected on the data nonlinearly. Although many manifold learning methods have been developed for such problems, most methods do not consider the spatial correlation between samples that is inherent and useful in remote sensing data. We propose a manifold learning method which directly combines the spatial proximity and the spectral similarity through kernel PCA framework. A gain factor caused by spatial proximity is first modelled with a heat kernel, and is added to the original similarity computed from the spectral values of a pair of samples. Parameters are tuned with intelligent grid search (IGS) method for the derived manifold coordinates to achieve optimal classification accuracies. Of particular interest is its performance with small training size, because labelled samples are usually scarce due to its high acquisition cost. The proposed spatial kernel PCA (KPCA) is compared with PCA in terms of classification accuracy with the nearest-neighbourhood classification method.

Keywords

References

  1. Bachmann, C. M., T. L. Ainsworth, and Fusina, R. A., 2006. Improved Manifold Coordinate Representations of Large-Scale Hyperspectral Scenes, IEEE Trans. on Geosci. and Remote Sens., 44: 2786-2803. https://doi.org/10.1109/TGRS.2006.881801
  2. Bachmann, C. M., T. L. Ainsworth, R. A. Fusina, M. J. Montes, J. H. Bowles, D. R. Korwan, and D. B. Gillis, 2009. Bathymetric Retrieval From Hyperspectral Imagery Using Manifold Coordinate Representations, Geoscience and Remote Sensing, IEEE Transactions on, 47: 884-897.
  3. Belkin, M. and P. Niyogi, 2003. Laplacian eigenmaps for dimensionality reduction and data representation, Neural Computation, 15: 1373-1396. https://doi.org/10.1162/089976603321780317
  4. Daughtry, C. S. T., E. R. Hunt, and J. E. McMurtrey, 2004. Assessing crop residue cover using shortwave infrared reflectance, Remote Sensing of Environment, 90: 126-134. https://doi.org/10.1016/j.rse.2003.10.023
  5. Green, A. A., M. Berman, P. Switzer, and M. D. Craig, 1988. A transformation for ordering multispectral data in terms of image quality with implications for noise removal, Geoscience and Remote Sensing, IEEE Transactions on, 26: 65-74.
  6. Ham, J., D. D. Lee, S. Mika, and B. Scholkopf, 2004. A kernel view of the dimensionality reduction of manifolds. Paper read at Proceedings of the twenty-first international conference on Machine learning at Banff, Alberta, Canada.
  7. Jacquemoud S. and F. Baret 1990. PROSPECT: A model of leaf optical properties spectra, Remote Sensing of Environment, 34: 75-91. https://doi.org/10.1016/0034-4257(90)90100-Z
  8. Kim, W. and M. M. Crawford, 2010. Adaptive Classification for Hyperspectral Image Data Using Manifold Regularization Kernel Machines, Geoscience and Remote Sensing, IEEE Transactions on, 48: 4110-4121.
  9. Kim, W., M. M. Crawford, and S. Lee, 2010. Integrating spatial proximity with manifold learning, International Symposium of Remote Sensing, 2010.
  10. Ma, L., Crawford, and J. Tian, 2010. Local manifold learning M. M. -Based k-Nearest-Neighbor for Hyperspectral Image Classification, Geoscience and Remote Sensing, IEEE Transactions on, 48:1-11.
  11. Roweis, S. T. and L. K. Saul, 2000. Nonlinear dimensionality reduction by local linear embedding. Science, 290: 2323-2326. https://doi.org/10.1126/science.290.5500.2323
  12. Scholkopf, B., A. J. Smola, and K. R. Muller, 1997. Kernel principal component analysis, Lecture notes in computer science, 1327: 583-588.
  13. Tenenbaum, J. B., V. de Silva, and J. C. Langford, 2000. A global geometric framework for nonlinear dimensionality reduction, IN Science, 290: 2319-2323. https://doi.org/10.1126/science.290.5500.2319
  14. Verhoef, W., 1984. Light scattering by leaf layers with application to canopy reflectance modeling: The SAIL model, Remote Sensing of Environment, 16: 125-141. https://doi.org/10.1016/0034-4257(84)90057-9