An Improvement of Type-2 Fuzzy Clustering Algorithm for Visual Fire Detection

This paper presents a novel approach for visual fire detection by modelling the spatial structure of fire, this structure is considered in terms of the color intensity of fire-color pixels. To model this structure, the authors uses an interval type-2 fuzzy clustering algorithm with some modification to separate fire-color pixels into some clusters, then these clusters are used to model the structure of fire. Experimental results show that our method is capable of detecting fire in early state and in the weak light-intensity environment. In addition, this method evaluates the structure of fire from a single image, so it can be integrated into the surveillance system or applied in automated retrieval of events in newscast videos in which the camera is dynamic.