Automated image-based fire detection and alarm system using edge computing and cloud-based platform

To tackle the increasing wildfire challenges, this paper presents an automated image-based fire detection and alarm system utilizing edge computing and a cloud-based platform, specifically designed for urban building fire detection. The system captures both RGB and infrared images from thermal cameras and employs computer vision techniques to detect fire characteristics such as flames and smoke. By integrating edge computing, the system minimizes latency, enhancing the accuracy of fire detection and alarm activation. The cloud platform supports extensive data storage, analysis, and remote monitoring, ensuring hihighly available and scalable data accessibility. The proposed system includes a detailed description of the system architecture design, data collection, and the selection and application of detection algorithms that leverage both RGB and thermal image data for fire detection. Using the campus building and surrounding risk-prone areas as a testbed, the proposed system demonstrated desired fire detection capabilities and a robust solution to quickly identify and respond to fire incidents within the urban area. The proposed system functionalities can be scaled and adapted to other fire risk-prone areas.