PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Spatio-Spectral Remote Sensing Image Classification With Graph Kernels
Nino Shervashidze, Gustavo Camps-Valls and Karsten Borgwardt
IEEE Geoscience and Remote Sensing Letters Volume 7, Number 4, pp. 741-745, 2010. ISSN 1545-598X

Abstract

This letter presents a graph kernel for spatio-spectral remote sensing image classification with support vector machines (SVMs). The method considers higher order relations in the neighborhood (beyond pairwise spatial relations) to iteratively compute a kernel matrix for SVM learning. The proposed kernel is easy to compute and constitutes a powerful alternative to existing approaches. The capabilities of the method are illustrated in several multi- and hyperspectral remote sensing images acquired over both urban and agricultural areas.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Theory & Algorithms
ID Code:8004
Deposited By:Nino Shervashidze
Deposited On:17 March 2011