Skip to Main content Skip to Navigation
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 metadatas

https://hal.inria.fr/inria-00494819
Contributor : Conférence Sfds-Hal <>
Submitted on : Thursday, June 24, 2010 - 8:59:15 AM
Last modification on : Thursday, June 24, 2010 - 8:59:15 AM
Long-term archiving on: : Monday, September 27, 2010 - 11:42:53 AM

File

p183.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00494819, version 1

Collections

Citation

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

Share

Metrics

Record views

382

Files downloads

466