Digital image based IoT intelligent fire detection with telegram notification

Due to inadequate handling, fire disasters often result in significant losses and even loss of life. A fire detection system is essential, especially in places prone to fire. In this study, a digital image-based IoT system was built using the YOLO (You Only Look Once) algorithm to detect and provide fire warnings quickly and accurately. This research was conducted to develop a fire detection system from existing research on IoT devices by combining it with digital image processing technology with the YOLOv8 algorithm, as well as integrating the IoT system into the Telegram instant messaging application. This study also combines a fire detection system with a fire sensor, MQ-2 temperature sensor, and MQ-2 smoke sensor. The study results show that the YOLOv8 nano model with ESP32-CAM can detect small flames from candles up to a distance of 220 cm. The ESP32 fire sensor can detect small flames up to a distance of 90 cm and large flames up to a distance of 140 cm. VPS can be sent to the Telegram application, just as the LM35 temperature sensor detects temperatures above 50ºC and the MQ-2 smoke sensor detects smoke levels above 450 ppm. All data obtained can be displayed on the VPS dashboard and the Telegram application.