Image Based Forest Fire Detection Using Dynamic Characteristics with Artificial Neural Networks

In this paper, we propose a real-time forest fire detection algorithm using artificial neural networks based on dynamic characteristics of fire regions segmented from video images. Fire region is obtained from image with the help of threshold values in HSV color space. Area, roundness and contour are computed for fire regions from each 5 continuous frames. The average and mean square deviation of them are used as dynamic characteristics, and taken as input of the artificial neural network. The trained BP network can help identify forest fire, even distinguish it from moving car or flying flag with red color. Experimental results of our method prove its value in forest fire surveillance.