A New Flame Detection Method Using Probability Model

A new flame detection method based on the probability model is proposed in the paper. It uses the color, the edge trembling and the spectrum of the flame height to eliminate the surrounding disturbances. Then, the probability model of the fire flame is established based on the theory of the degree of belief. The model can handle practical complex situations. The experiment results show that the method processes image quickly at the rate of 25 frames a second. And the method remains with stronger anti-jamming ability and higher accuracy. In our experiments, the suspected probability of street lamps and automotive lamps is lower than 10% and the suspected probability of the flame is 100%. At last, the comparing results with two other methods show that the flame detection method based on the probability has better capabilities