AN AUTOMATE MOBILE APPLICATION FOR FIRE DETECTION USING DEEP LEARNING

Abstract

As a new fire detection technolog}, image fire detection has recentlv played a important role in reducing fire losses by alarming users early through early fire detection. Image fire detection is based on an algorithmic analysis ofimages. However, there is a lower accuracy, delayed detection, and a large amount of computation in common detection algorithms, including manually and machine automatical!} extracting image features. Therefore, novel image fire detection algorithms based on the advanced object detection CNN models. A comparison between proposed and current systems reveals that the accuracy of fire detection algorithms is depend on object detection CNNs is higher than other algorithms. We use TensorFlow in our piv>wL iensorFlo,. i> a P}thon library for fast numerical computing created arJ released by Googie. It is a foundation library that can be used to create Deep Lcv.nimg models direct!} or by using wrapper libraries that simplify the process built on ton TensorFlow.