A Novel Computational Approach for Fire Detection

This paper proposes a model for detecting fire captured in video data by combining the methods of correlation coefficient, Gaussian Mixture Model - GMM and turbulent analysis. The method of correlation efficient is used to determine movement objects. We use GMM to cluster fire-colored pixel in the RGB space. The objective of turbulent analysis is to detect the flame of fire. A model built on three above methods will be presented and the experimental results are discussed in Section III.