A novel boiler flame image segmentation and tracking algorithm based on YCbCr color space

The process of coal powder burning in the boiler is a complex and unstable suspended combustion process, so the flame image segmentation and tracking are quite difficult. In this paper, a flame image automatic threshold segmentation and tracking algorithm based on YCbCr space is proposed. The proposed algorithm uses YCbCr color space to separate the luminance from the chrominance more effectively than in color spaces such as RGB. The proposed algorithm is tested on two types of video sequence: image sequence of flames burning acutely and of flames about to extinguish. The experimental results indicate that it is a concise method of high speed and efficiency, and the central area of the flame can be segmented and tracked effectively through the proposed algorithm. Furthermore the proposed color space and algorithm can be used for real-time flame detection in the furnace.