A novel smoke detection method using support vector machine

An early and certain fire detection is one of the important issue to keep safe infrastructures. Especially, it becomes an urgent problem in large facilities like port facilities, large factories and power plants, due to its large harmful effect to surrounding areas. In these places, smoke is an important and useful sign to detect the fire robustly even in such open areas. In this study, we present a novel and robust smoke detection method based on image information. Firstly we extract moving objects of images as smoke candidate regions in a pre-processing. Because smoke has a characteristic pattern as image information, we treat smoke patterns as textures. Here we use texture analysis to extract feature vectors of images. To classify extracted moving objects are smoke or non-smoke, we use support vector machine(SVM) with texture features as input features. Extraction of moving objects are sometimes easily affected by environmental conditions. So we accumulate the result of the classification with SVM about time to obtain accurate extraction results of smoke regions.