Image time-series mining

Author

Heas, Patrick ; Marthon, Philippe ; Datcu, Mihai ; Giros, Alain

Author_Institution

Inst. de Recherche en Informatique de Toulouse, France

Volume

4

fYear

2004

fDate

20-24 Sept. 2004

Firstpage

2420

Abstract

A visual information mining concept is proposed for spatio-temporal patterns discovery in remotely sensed image time-series (ITS). An information theory framework is adopted to first model information content. It results in the inference of a relevant directed graph characterizing ITS. Then the user conjecture is modeled via visual information representations: similarity measures between sub-graphs, which represents spatio-temporal events are derived and included in an interactive learning and probabilistic retrieval procedure of user-specific event-types. The present concept for ITS mining is demonstrated on multitemporal SPOT data.

Keywords

data acquisition; data mining; geophysical techniques; geophysics computing; information retrieval; information theory; learning (artificial intelligence); remote sensing; time series; directed graph; image time series mining; inference; information content; information theory; multitemporal SPOT data; probabilistic retrieval; remote sensing; spatiotemporal pattern discovery; user conjecture; visual information mining; visual information representation; Data mining; Image databases; Image sensors; Information representation; Information retrieval; Information systems; Information theory; Multidimensional systems; Satellites; Spatiotemporal phenomena;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2004. IGARSS '04. Proceedings. 2004 IEEE International

Print_ISBN

0-7803-8742-2

Type

conf

DOI

10.1109/IGARSS.2004.1369779

Filename

1369779