Advancing Fire Detection: A One-Stage Object Detection Approach Using YOLOv5 and YOLOv8 Models

DOI

10.2991/978-94-6463-496-9_4How to use a DOI?

Keywords

Fire Detection; Deep learning; YOLOv5; YOLOv8

Abstract

Fire accidents present considerable risks on a global scale, leading to considerable losses in life, property, and the environment. Traditional sensing technologies face challenges in effectively detecting fires, particularly in large areas. Deep learning approaches have been explored for fire detection systems, but challenges remain, particularly in scenarios like indoor and forest fires, and distinguishing between fires with or without smoke. These challenges lead to environmental losses and long recovery periods. In this paper, our objective was to tackle these challenges by presenting a solution utilizing a one-stage object detection method for identifying flames and smoke, where we focused on covering indoor, outdoor, and forest fires. We employed YOLOv8 and YOLOv5 models in several gathered datasets, aiming for an accurate model. Evaluation yields a mAP@0.5 of 93% with YOLOv8. Based on the results, the best-obtained model was integrated into the implementation of a live stream-detecting application.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Maroua Cheknane
AU  - Saida Sarra Boudouh
AU  - Tahar Bendouma
PY  - 2024
DA  - 2024/08/31
TI  - Advancing Fire Detection: A One-Stage Object Detection Approach Using YOLOv5 and YOLOv8 Models
BT  - Proceedings of the International Conference on Emerging Intelligent Systems for Sustainable Development (ICEIS 2024)
PB  - Atlantis Press
SP  - 37
EP  - 49
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-496-9_4
DO  - 10.2991/978-94-6463-496-9_4
ID  - Cheknane2024
ER  -