Evaluation on SPOT data of classification algorithms based on Markovian modelization

Author

Cubero-Castan, E. ; Pons, I. ; Zerubia, J.

Author_Institution

CNES, Toulouse, France

Volume

1

fYear

34881

fDate

10-14 Jul1995

Firstpage

115

Abstract

CNES (French Space Agency) has developed a research program related to SPOT imagery to deal with cartography topics. Many studies, conducted with different laboratories, are intended to work on remote sensing data. The main purpose of the present research is information extraction (network extraction, urban area extraction, segmentation, etc.) One of these studies, made in collaboration with INRIA Sophia Antipolis, intends to classify remote sensing images using MRF (Markov random field) modelization. The paper presents an experiment, conducted by GEOSYS, on crop surveys. An evaluation of the MRF based algorithms is proposed to estimate the results in a supervised context, in order to validate this new approach. A comparison between the proposed methods and standard classification techniques have been done on multispectral SPOT data (XS1, XS2, XS3)

Keywords

Markov processes; cartography; farming; image classification; random processes; remote sensing; Markov random field; Markovian modelization; cartography; classification algorithms; crop surveys; information extraction; multispectral SPOT data; remote sensing data; Classification algorithms; Collaborative work; Crops; Data mining; Image segmentation; Laboratories; Passive optical networks; Remote sensing; Testing; Urban areas;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 1995. IGARSS '95. 'Quantitative Remote Sensing for Science and Applications', International

Conference_Location

Firenze

Print_ISBN

0-7803-2567-2

Type

conf

DOI

10.1109/IGARSS.1995.519664

Filename

519664