Skip to Main content Skip to Navigation
New interface
Conference papers

Second order statistics for hyperspectral data classification

Abstract : Hyperspectral imagery classification, taking into account spectral and spatial features, is a promising task in remote sensing field. In this paper, the incorporation of second order statistics in hyperspectral data classification using support vector machines is proposed. The effect of using the semivariance geostatistic as a spatial feature rather than first order statistics (mean and standard deviation) is tested. The overall classification accuracy is evaluated for the AVIRIS Indian Pines-1992 benchmark data set. Empirical results show that the proposed approach gives better performance than the method based on first order statistics
Complete list of metadata
Contributor : Conférence Sfds-Hal Connect in order to contact the contributor
Submitted on : Thursday, June 24, 2010 - 8:59:15 AM
Last modification on : Wednesday, October 28, 2020 - 10:04:02 AM
Long-term archiving on: : Monday, September 27, 2010 - 11:42:53 AM


Files produced by the author(s)


  • HAL Id : inria-00494819, version 1



Saoussen Bahria, Mohamed Limam. Second order statistics for hyperspectral data classification. 42èmes Journées de Statistique, 2010, Marseille, France, France. ⟨inria-00494819⟩



Record views


Files downloads