Forest fire detection based on Gaussian field analysis

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 fire detection from TIR satellite images based on the random field theory. First, preprocessing is used to model the image as a realization of a Gaussian field which presents interesting properties. The fire areas which are supposed to be a minority are considered as anomalies of that field. 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 field). We then extend this application to the estimation of the fire propagation direction.