Fire detection using neural network

Abstract

This study aims to investigate the effectiveness of image processing by using artificially neural network to detect fire in the room by using camera. This uses features of flame images in a simulation fire as input elements, is considered. Flame images are taken from the dynamic image, and features of the images for the ANN application are extracted from a rectified image which considers the difference in distance from the CCD color to the fire source. © 2006 ICASE.