Implementation fire detection algorithm using fixed point digital signal processor

Abstract

In this paper, a fire detection algorithm based on video processing is proposed. Probability feature of smoke and flame is model by Gaussian mixture model. The whole process is divided into three parts, candidate flame or smoke selection, Gaussian mixture model calculation, and flame or smoke decision. The algorithm was implemented with fixed point DSP. As results of experiments, it is shown that the proposed algorithm and implemented video processing board effectively detects smokes and flames. © 2011 Springer-Verlag.