On the Influence of Spatial Information for Hyper-spectral Satellite Imaging Characterization

  • Olga Rajadell
  • Pedro García-Sevilla
  • Filiberto Pla
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6669)


Land-use classification for hyper-spectral satellite images requires a previous step of pixel characterization. In the easiest case, each pixel is characterized by its spectral curve. The improvement of the spectral and spatial resolution in hyper-spectral sensors has led to very large data sets. Some researches have focused on better classifiers that can handle big amounts of data. Others have faced the problem of band selection to reduce the dimensionality of the feature space. However, thanks to the improvement in the spatial resolution of the sensors, spatial information may also provide new features for hyper-spectral satellite data. Here, an study on the influence of spectral-spatial features combined with an unsupervised band selection method is presented. The results show that it is possible to reduce very significantly the number of spectral bands required while having an adequate description of the spectral-spatial characteristics of the image for pixel classification tasks.


Feature Vector Spectral Band Hyperspectral Image Hyperspectral Data Gabor Feature 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Martínez-Usó, A., Pla, F., García-Sevilla, P.: Clustering-based hyperspectral band selection using information measures. IEEE Trans. on Geoscience & Remote Sensing 45, 4158–4171 (2007)CrossRefGoogle Scholar
  2. 2.
    Yang, H., Meer, F., Bakker, W., Tan, Z.: A back-propagation neural network for mineralogical mapping from aviris data. International Journal of Remote Sensing 20, 97–110 (1999)CrossRefGoogle Scholar
  3. 3.
    Zhou, H., Mao, Z., Wang, C.: Classification of coastal areas by airbone hyperspectral image. In: Proceedings of SPIE, pp. 471–476 (2005)Google Scholar
  4. 4.
    Chen, C., Ho, P.: Statistical pattern recognition in remote sensing. Pattern Recognition 41, 2731–2741 (2008)CrossRefzbMATHGoogle Scholar
  5. 5.
    Camps-Valls, G., Bruzzone, L.: Kernel-based methods for hyperspectral image classification. IEEE Trans. on Geoscience & Remote Sensing 43, 1351–1362 (2005)CrossRefGoogle Scholar
  6. 6.
    Plaza, A., et al.: Recent advances in techniques for hyperspectral image processing. Remote Sensing of Environment 113, 110–122 (2009)CrossRefGoogle Scholar
  7. 7.
    Landgrebe, D.A.: Signal Theory Methods in Multispectral Remote Sensing. Wiley, Hoboken (2003)CrossRefGoogle Scholar
  8. 8.
    Petrou, M., García-Sevilla, P.: Image Processing: Dealing with Texture. John-Wiley and Sons, West Sussex (2006)CrossRefGoogle Scholar
  9. 9.
    Jimenez, L., Landgrebe, D.: Hyperspectral data analysis and supervised feature reduction via projection pursuit. IEEE Trans. on Geoscience and Remote Sensing 37(6), 2653–2667 (1999)CrossRefGoogle Scholar
  10. 10.
    Manjunath, B., Ma, W.: Texture features for browsing and retrieval of image data. IEEE Trans. on Pattern Analysis and Machine Intelligence 18(8), 837–842 (1996)CrossRefGoogle Scholar
  11. 11.
    Rajadell, O., García-Sevilla, P., Pla, F.: Filter banks for hyperspectral pixel classification of satellite images. In: Bayro-Corrochano, E., Eklundh, J.-O. (eds.) CIARP 2009. LNCS, vol. 5856, pp. 1039–1046. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  12. 12.
    Fogel, I., Sagi, D.: Gabor filters as texture discriminator. Biological Cybernetics 61, 103–113 (1989)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Olga Rajadell
    • 1
  • Pedro García-Sevilla
    • 1
  • Filiberto Pla
    • 1
  1. 1.Depto. Lenguajes y Sistemas InformáticosJaume I UniversityCastellónSpain

Personalised recommendations