Robust Little Flame Detection on Real-Time Video Surveillance System

Abstract

This study proposed a method to detect the little flame in the early stage of fire combustion. The foreground object was extracted by motion detection and YCb Cr color clues. To avoid the noise of motion detection in different resolution videos, background edge model is used to eliminate noise instead of morphology. Next, with the help of fire characteristics, the foreground object is identified. A fire object is determined by compactness, corner flicker rate, and growth rate. The experiment can be applied to any resolution video and complex scene, both indoors and outdoors, such as squares, where people walk around and vehicles pass by. The outcome of experiment, using this proposed method, can detect the fire object accurately and exclude the undangerous fire.