Skip to Main content Skip to Navigation
Conference papers

Parsimonious Gaussian Process Models for the Classification of Multivariate Remote Sensing Images

Mathieu Fauvel 1 Charles Bouveyron 2 Stephane Girard 3
3 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : A family of parsimonious Gaussian process models is presented. They allow to construct a Gaussian mixture model in a kernel feature space by assuming that the data of each class live in a specific subspace. The proposed models are used to build a kernel Markov random field (pGPMRF), which is applied to classify the pixels of a real multivariate remotely sensed image. In terms of classification accuracy, some of the proposed models perform equivalently to a SVM but they perform better than another kernel Gaussian mixture model previously defined in the literature. The pGPMRF provides the best classification accuracy thanks to the spatial regularization.
Complete list of metadata

Cited literature [11 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01062378
Contributor : Stephane Girard <>
Submitted on : Tuesday, September 9, 2014 - 4:52:37 PM
Last modification on : Thursday, May 13, 2021 - 3:45:11 AM
Long-term archiving on: : Wednesday, December 10, 2014 - 2:15:13 PM

File

fauvel_icassp14.pdf
Files produced by the author(s)

Identifiers

Citation

Mathieu Fauvel, Charles Bouveyron, Stephane Girard. Parsimonious Gaussian Process Models for the Classification of Multivariate Remote Sensing Images. ICASSP 2014 - IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2014, Florence, Italy. pp.2913-2916, ⟨10.1109/ICASSP.2014.6854133⟩. ⟨hal-01062378⟩

Share

Metrics

Record views

1802

Files downloads

1260