Artificial intelligence based real-time smoke and fire detection and security management algorithms

Abstract

Smart fire detection is essential for people’s safety and property. The effective utilization of innovative technologies provides fast fire detection before intensification. Automatic fire systems commonly utilize passive sensors that are damaged by sunlight and environmental conditions. To address this problem, this study provides AI-based fire and smoke detection system that uses a You Only Look Once (YOLO) smart object detection algorithm integrated with a deep learning convolutional neural network architecture(CNN) and Android Studio to achieve the desired requirements. This prototype uses Common Objects in Context (COCO) datasheets for YOLO modelling. The incorporated camera continuously monitors the consumer for immediate notification. The system uses Android applications to monitor the parameters. The application architecture uses the Django framework to communicate the developed system with the Android application and the YOLO model. The Android application was designed using Android studio software to provide online information via cloud-based systems. Compared with conventional fire detection systems that consist of heat, flame, gas, and smoke sensors with high power consumption, installation, and preventive maintenance. The designed system considers AI fire detection algorithms using images and video forms. Further advancements in this state-of-the-art technology can improve the industrial application of early fire detection.