Title: Real-time fire detection and alarm system using edge computing and cloud IoT platform

Authors: Chenglin Guo; Yong Bai; Mei Wu; You Zhou

Addresses: Hainan University, Haikou, Hainan, China ' Hainan University, Haikou, Hainan, China ' Hainan University, Haikou, Hainan, China ' Hainan University, Haikou, Hainan, China

Abstract: Fires often cause huge loss of personnel and property, hence it is very important to monitor fires and send alarms to users in real time. With the development of the Internet of Things (IoT) technology, intelligent edge devices can reduce delay in fire detection. However, there are still some problems with using edge devices for fire monitoring, such as the lack of data set of electrical fires in the city in the open source fire data set, the transmission capacity of edge devices is not enough to transmit massive detection data to the cloud, and the computing power of edge devices is not enough to run deep learning neural network models in real time. This paper proposes a real-time video fire monitoring and alarm system based on edge computing and cloud IoT platform. The intelligent edge device is implemented based on Nvidia Jetson Nano with object detection network YOLOv5s deployed for fire detection where YOLOv5s is accelerated by TensorRT and DeepStream. Then real-time message notification is performed with local server, and fire event and metadata can be further delivered to the Azure IoT platform. The experiment demonstrates that it is effective for real-time fire detection and message notification with our proposed system.

Keywords: fire detection; IoT; DeepStream; edge computing; deep learning.

DOI: 10.1504/IJWMC.2022.124822

International Journal of Wireless and Mobile Computing, 2022 Vol.22 No.3/4, pp.310 - 318

Received: 12 Oct 2021
Accepted: 27 Feb 2022

Published online: 09 Aug 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article