Digital Image Processing based Fire Flame Color and Oscillation Frequency Analysis

Two distinctive fire flame characteristics, i.e., color information and flickering are discussed in this paper to provide basic criteria to improve the anti-jamming ability and reliability of the video flame detection technology in complex scenes. An effective real-time flame color detection criterion is firstly proposed by the method of two-dimensional color space reconstruction and saturation fitting for the manually collected flame-pixel sample database. The flame size and accumulated gray value are then extracted to construct the time series of video sequences of four combustion experiments. At last, the oscillation frequency of the flame flickering is calculated by performing the Fourier Transform for these time series. It is found that oscillation frequencies are in good agreement with the ones calculated by Pagni's law. The results of this paper can be used as bases of multi-feature fusion video flame detection method.