Flame detection algorithm based on a saliency detection technique with prior information in the YCbCr color space

Computer vision-based Are detection involves flame detection and smoke detection. This paper proposes a new flame detection algorithm, which is based on a saliency detection technique with prior information in color space. In still images and video sequences, an area containing a flame always attracts the attention because it is an exceptional event. Thus, to utilize the color information of flame pixels, the probability density function of the flame pixel color can be obtained using Parzen window nonparametric estimation. This prior probability density function is then fused with the saliency detection phase as top-down information so the flame candidate area can be extracted. According to the experimental results, our proposed method can reduce the number of false alarms greatly compared with an alternative algorithm, while it also ensures the accurate classification of positive samples. The classification performance of our proposed method was better than that of alternative algorithms.