A new fire detection method based on integrated features

Abstract

Because of high fire frequency and huge losses, the research of fire signal detection in the monitoring system is an important task in the fire-preventing field. A new fire signal detection method based on integrated features of flame is proposed in the paper. With the difference of background and foreground objects achieved in video, the moving target can be detected to judge if there are characteristics of flame, which includes color and saturation, flashing characteristics, spatial wavelet energy and circularity. The fire signal detection method presented can overcome the shortcomings that exist in some traditional methods i.e. it can surmount the large impact on environmental interference factors, such as temperature, photographic and smoke of environment. By a large amount of experiments, it shows clearly that the error rate of flame recognition is low, and also the real-time ability and the anti-disturbance ability are very good.