Deep Learning Based Fire Detection, Alert and Suppression System

The biggest and most dangerous threat to any enterprise is fire. The primary causes of fire include static electricity, overheating, human mistake, environmental factors, and equipment failure. In this project, issues with current methods for detecting fire in industrial settings have been highlighted, and an original approach to address the issues has been put forth, thereby offering functions like alarm, detection, and suppression. This project uses an Arduino-powered fire detector and a security camera, and it applies the ideas of image processing and deep learning to produce results for real-time detection. Convolutional Neural Network (CNN)/MobileNet-v2 is used in this research to detect the proper image of fire and perform image pre-processing. There have been numerous large-scale fires and bad fire imagery in a lot's of circumstance, having both interior (e.g., homes, offices, factories) and external (e.g., depository or cache areas). A low-cost embedded device (Jetson Nano or raspberry pie) that consists of a single, fixed camera for individual backdrop and functions in the seeable spectral range can also be used to implement this job. The video camera used for surveillance doesn't need to meet any particular specifications. The camera will continue to keep an eye on the surroundings of the room so long as the device is activated. If a fire is found in the frame, CNN will process the fire image before processing the alert message and sending it via email to the user's smartphone, alarm sound, and water pump to put out the fire.