A methodology for fire detection using colour pixel classification

Abstract

Lately, fire outbreaks are common issues and its occurrence could cause severe damage toward nature and human properties. Thus, fire detection has been an important issue to protect human life and property and has increases in recent years. This paper focusing on the algorithm of fire detection using image processing techniques i.e. colour pixel classification. This Fire detection system does not require any special type of sensors and it has the ability to monitor large area and depending on the quality of camera used. The objective of this research is to design a methodology for fire detection using image as input. The propose algorithm is using colour pixel classification. This system used image enhancement technique, RGB and YCbCr colour models with given conditions to separate fire pixel from background and isolates luminance from chrominance contrasted from original image to detect fire. The propose system achieved 90% fire detection rate on average.