A New Color-Based Segmentation Method for Forest Fire from Video Image

This paper proposes a new color-based method for forest fire segmentation from video image. Two kinds of color features including intensity value and color distribution are used. In segmentation based on V value of HSV color model, the lower threshold is defined from experience, and the higher threshold value is computed automatically, thus the possible fire regions can be divided into two subsets accordingly. In segmentation based on color distribution, fire color samples are collected and then projected onto HS, HV and SV planes. One pixel can be decided as fire or not quickly by checking whether its color values lie within the distribution ranges of the three 2D planes at the same time. Final fire regions are generated from these two segmentation results. Our method is tested on some video images with fire and the results are encouraging.