Forest fire detection based on Gaussian field analysis - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2007

Forest fire detection based on Gaussian field analysis

Florent Lafarge
  • Function : Author
  • PersonId : 833647
Xavier Descombes
Josiane Zerubia
  • Function : Author
  • PersonId : 833424


The Thermical InfraRed (TIR) channel contains wave lengths sensitive to the emission of heat. The forest fires can be characterized by intensity peaks on TIR images. We present a fully automatic method of forest fi re detection from TIR satellite images based on the random fi eld theory. First, preprocessing is used to model the image as a realization of a Gaussian fi eld which presents interesting properties. The fire areas which are supposed to be a minority are considered as anomalies of that fi eld. We present a statistical analysis of Gaussian field to determine a degree of belonging of a cluster to the image background (i.e. a realization of a Gaussian fi eld). We then extend this application to the estimation of the fi re propagation direction.
Fichier principal
Vignette du fichier
2007-eusipco.pdf (896.92 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00781765 , version 1 (28-01-2013)


  • HAL Id : hal-00781765 , version 1


Florent Lafarge, Xavier Descombes, Josiane Zerubia. Forest fire detection based on Gaussian field analysis. European Signal Processing Conference (EUSIPCO), Sep 2007, Poznan, Poland. ⟨hal-00781765⟩
265 View
165 Download


Gmail Facebook X LinkedIn More