Fire detection using image processing

Abstract

A number of methods have been developed to detect fire. The working principle of conventional fire detectors is based on physical properties of fire (e.g., smoke, heat, temperature).

This paper describes the detection of fire by processing images of fire. Image processing and computer vision techniques are used to extract key characteristics of fire detection. The algorithm combines color information of the fire with the edge of the fire information. Based on the combined results of both techniques, a parameter is created to segment out the necessary details from the images to detect and identify the fire. The source code for fire detection is written in MATLAB. 30 sample images were tested to detect fire to test the performance of the algorithm introduced in this paper.