Advertisement

Classification of Hyperspectral Images Compressed through 3D-JPEG2000

  • Ian Blanes
  • Alaitz Zabala
  • Gerard Moré
  • Xavier Pons
  • Joan Serra-Sagristà
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5179)

Abstract

Classification of hyperspectral images is paramount to an increasing number of user applications. With the advent of more powerful technology, sensed images demand for larger requirements in computational and memory capabilities, which has led to devise compression techniques to alleviate the transmission and storage necessities.

Classification of compressed images is addressed in this paper. Compression takes into account the spectral correlation of hyperspectral images together with more simple approaches. Experiments have been performed on a large hyperspectral CASI image with 72 bands. Both coding and classification results indicate that the performance of 3d-DWT is superior to the other two lossy coding approaches, providing consistent improvements of more than 10 dB for the coding process, and maintaining both the global accuracy and the percentage of classified area for the classification process.

Keywords

JPEG2000 standard 3-dimensional coding hyperspectral images classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jensen, J.: Introductory Digital Image Processing. A Remote Sensing Perspective. Pearson Prentice Hall, London (2005)Google Scholar
  2. 2.
    Taubman, D.S., Marcellin, M.W.: JPEG 2000: Image Compression Fundamentals, Standards, and Practice. Kluwer Academic Publishers, Dordrecht (2002)Google Scholar
  3. 3.
    Li, Z., Yuan, X., Lam, K.W.: Effects of JPEG compression on the accuracy of photogrammetric point determination. Photogrammetric Engineering and Remote Sensing 68(8), 847–853 (2002)Google Scholar
  4. 4.
    Shih, T.Y., Liu, J.K.: Effects of JPEG 2000 compression on automated dsm extraction: evidence from aerial photographs. The Photogrammetric Record 20, 351–365 (2005)CrossRefGoogle Scholar
  5. 5.
    Zabala, A., Pons, X., Diaz-Delgado, R., Garcia, F., Auli-Llinas, F., Serra-Sagrista, J.: Effects of JPEG and JPEG2000 lossy compression on remote sensing image classification for mapping crops and forest areas. In: IGARSS 2006, pp. 790–793. IEEE, Los Alamitos (2006)Google Scholar
  6. 6.
    Tintrup, F., De Natale, F., Giusto, D.: Automatic land classification vs. data compression: a comparative evaluation. In: Proceedings of IGARSS 1998, vol. 4, pp. 1751–1753. IEEE, Los Alamitos (1998)Google Scholar
  7. 7.
    Penna, B., Tillo, T., Magli, E., Olmo, G.: Transform coding techniques for lossy hyperspectral data compression. IEEE Trans. Geoscience Remote Sensing 45(5), 1408–1421 (2007)CrossRefGoogle Scholar
  8. 8.
    Palà, V., Alamús, R., Pérez, F., Arbiol, R., Talaya, J.: El sistema CASI-ICC: un sensor multiespectral aerotransportado con capacidades cartográficas. In: Revista de Teledetección, Asociación Española de Teledetección, vol. 12, pp. 89–92 (1999)Google Scholar
  9. 9.
    Tang, X., Pearlman, W.A.: Three-Dimensional Wavelet-Based Compression of hyperspectral Images. In: Hyperspectral Data Compression, pp. 273–308. Springer, USA (2006)CrossRefGoogle Scholar
  10. 10.
    Yeh, P.S., Armbruster, P., Kiely, A., Masschelein, B., Moury, G., Schaefer, C., Thiebaut, C.: The New CCSDS Image Compression Recommendation. In: Aerospace Conference, vol. 5-12, pp. 4138–4145. IEEE, Los Alamitos (2005)Google Scholar
  11. 11.
    Ramakrishna, B., Plaza, A., Chang, C.I., Ren, H., Du, Q., Chang, C.C.: Spectral/Spatial Hyperspectral Image Compression. In: Hyperspectral Data Compression, pp. 309–346. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  12. 12.
    Serra, P., Pons, X., Saurí, D.: Post-classification change detection with data from different sensors. Some accuracy considerations. International Journal of Remote Sensing 24(16), 3311–3340 (2003)Google Scholar
  13. 13.
    Pons, X., Moré, G., Serra, P.: Improvements on Classification by Tolerating NoData Values. Application to a Hybrid Classifier to Discriminate Mediterranean Vegetation with a Detailed Legend Using Multitemporal Series of Images. In: IEEE IGARSS and 27th CSRS, Denver, pp. 192–195 (2006)Google Scholar
  14. 14.
    Duda, R.D., Hart, P.E.: Pattern Classification and Scene Analysis. John Wiley & Sons, New York (1973)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Ian Blanes
    • 1
  • Alaitz Zabala
    • 2
  • Gerard Moré
    • 3
  • Xavier Pons
    • 2
    • 3
  • Joan Serra-Sagristà
    • 1
  1. 1.Department of Information and Communications Engineering  
  2. 2.Department of Geography  
  3. 3.Centre for Ecological Research and Forestry Applications (CREAF)Universitat Autònoma de Barcelona08290Spain

Personalised recommendations