Skip to Main Content
Forest fire, if not detected early enough, can cause great damage. In order to reduce it, it is important to detect fire as soon as possible and take actions to it. In this paper we propose a new image detection method for identifying fire in videos. The method analyzes the frame-to-frame change in given features of potential fire regions. These features are color, boundary roughness and skewness of the estimated fire regions. Because of flickering and random characteristics of fire, these are powerful discriminants. Using these statistical features, the results are combined according to the Bayes classifier to achieve a decision (i.e. fire happens, fire does not happen). Experiments illustrated the applicability of the method.