- Issue
- Journal of Siberian Federal University. Engineering & Technologies. 2024 17 (2)
- Authors
- Dheyab, Omer A. Dheyab; Chernikov, Dmitry Yu.; Selivanov, Alexander S.
- Contact information
- Omer A. Dheyab: Siberian Federal University Krasnoyarsk, Russian Federation; University of Technology-Iraq Baghdad, Iraq; Omer.A.Dheyab@uotechnology.edu.iq; Chernikov, Dmitry Yu.: Siberian Federal University Krasnoyarsk, Russian Federation; Selivanov, Alexander S. : Siberian Federal University Krasnoyarsk, Russian Federation
- Keywords
- visual sensor network; WebRTC; YOLOv5; surveillance camera; fire detection; WebRTC; YOLOv5
- Abstract
One of the most destructive natural disasters that harms both the environment and human life is fire. They jeopardize human life and public safety in addition to causing enormous material damages. The development of an effective system for identifying city fires is the aim of this project. An AI method for enhancing fire detection operations is the YOLOv5 model. For precise and effective fire detection, city cameras are turned into a visual sensor network based on the YOLOv5 paradigm. This system scans camera footage to determine the specific location and presence of fires using deep learning technologies. WebRTC technology is also used to send fire alarms. WebRTC enables direct and efficient communication between the system and observers. Combining YOLOv5 and WebRTC with a visual sensor network can enhance and increase the effectiveness of early fire detection and response operations. This study presents a system for early identification of fire incidents in cities, at a low cost by taking advantage of the existing surveillance camera infrastructure
- Pages
- 266–275
- EDN
- UBMXVW
- Paper at repository of SibFU
- https://elib.sfu-kras.ru/handle/2311/152769
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).