Python Based Comparative Study of Video Based Fire Detection

Abstract

Fire disasters are among the top 3 disasters that cause high amount of loss to both property and life. A system that is reliable, fast and can detect fire at an early stage is highly in demand.  Fire Detection system can be used in CCTV video and doesn't require higher cost. These early and timely given warnings can save a lot of life and property. The commonly used methods are typically based on color and motion.  There are many classifiers that can be used to differentiate between positive and non-positive pixels.  In this opportunity we will create a fire detector system using different computer vision algorithms based on their accuracy, speed and other parameter and Internet of Things (IOT) in order to get the real-time detection results.  Various Algorithm (such as HAAR, LBP, CNN) is used for the preprocessing of image, to detect the correct image of fire. As long as the camera will continue to monitor the conditions in the room.  If there is a fire detected by the camera, then the fire image will be processed using Image Processing and the result is a data string sent to the server and forwarded to the user’s smartphone (using the concept of IOT) as a warning (alert).