Fire accidents have become one of the major threats to the properties and safety of human beings. Since conventional detection methods often fail to detect fire accidents in their early stages, detection technologies based on video images have become an important alternative for early detection of fire accidents. In this paper, we develop a new method that can accurately detect smoke that often appears in early stages of a fire accident. The method processes video images and identifies regions that may contain moving targets with a background subtraction approach using a Gaussian Mixture Model. A number of static features associated with these regions are then extracted and analyzed based on the corresponding features of smoke regions, which can recognize and eliminate regions that are similar to smoke regions but do not contain smoke. Our testing results show that the impacts from weather and other external environments can then be effectively reduced with this new approach and fire smoke can be accurately and quickly detected with a low false alarm rate.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.