Share Email Print
cover

Proceedings Paper

Mixed spectral-structural classification of very high resolution images with summation kernels
Author(s): Devis Tuia; Frédéric Ratle
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper, mixed spectral-structural kernel machines are proposed for the classification of very-high resolution images. The simultaneous use of multispectral and structural features (computed using morphological filters) allows a significant increase in classification accuracy of remote sensing images. Subsequently, weighted summation kernel support vector machines are proposed and applied in order to take into account the multiscale nature of the scene considered. Such classifiers use the Mercer property of kernel matrices to compute a new kernel matrix accounting simultaneously for two scale parameters. Tests on a Zurich QuickBird image show the relevance of the proposed method : using the mixed spectral-structural features, the classification accuracy increases of about 5%, achieving a Kappa index of 0.97. The multikernel approach proposed provide an overall accuracy of 98.90% with related Kappa index of 0.985.

Paper Details

Date Published: 9 October 2008
PDF: 10 pages
Proc. SPIE 7109, Image and Signal Processing for Remote Sensing XIV, 710906 (9 October 2008); doi: 10.1117/12.799860
Show Author Affiliations
Devis Tuia, Univ. of Lausanne (Switzerland)
Frédéric Ratle, Univ. of Lausanne (Switzerland)


Published in SPIE Proceedings Vol. 7109:
Image and Signal Processing for Remote Sensing XIV
Lorenzo Bruzzone; Claudia Notarnicola; Francesco Posa, Editor(s)

© SPIE. Terms of Use
Back to Top