Machine Learning and Sensor-Based Real-Time Fire Detection Using YOLOv8
摘要
Fire causes numerous disasters and is a giant waste of resources and daily goods for humans. Therefore, automatic fire detection is needed to save mortal life. Here, proposed model adopt object detection using YOLOv8 with the help of a machine-learning approach has been designed which uses a temperature sensor and Arduino for sensing a certain range of temperature. The sensor senses the temperature of the surroundings if it crosses the desired range, an alarm is sounded and an image is captured using a camera, which is then sent to the email address of the user and also sent an SMS call notification. The performance of the proposed YOLOv8 has been evaluated by considering different metrics. The design of the approach is discussed elaborately followed by the flowchart and its working block diagram. A real-time experiment has been conducted to show the efficiency of the proposed approach to detect the fire.