A fire detection algorithm based on improved YOLOv5

Bo Yin

doi:10.1117/12.3026293

1 April 2024 A fire detection algorithm based on improved YOLOv5

Bo Yin

Proceedings Volume 13082, Fourth International Conference on Mechanical Engineering, Intelligent Manufacturing, and Automation Technology (MEMAT 2023); 130820R (2024) https://doi.org/10.1117/12.3026293
Event: 2023 4th International Conference on Mechanical Engineering, Intelligent Manufacturing and Automation Technology (MEMAT 2023), 2023, Guilin, China

Abstract

This paper proposes a fire detection algorithm based on improved YOLOv5 to address the issues of delayed and prone to false alarms in traditional fire systems. The proposed algorithm adopts the anchor-free object detection method, which reduces the number of parameters of the deep learning network model to improve reasoning speed. In addition, this proposed algorithm improves the precision of target detection by improving YOLOv5 backbone network structure, neck structure and detection head. The experimental simulation results show that the detection accuracy of proposed algorithm can reach 72.2%, which can effectively realize the intelligent fire detection.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Bo Yin "A fire detection algorithm based on improved YOLOv5", Proc. SPIE 13082, Fourth International Conference on Mechanical Engineering, Intelligent Manufacturing, and Automation Technology (MEMAT 2023), 130820R (1 April 2024); https://doi.org/10.1117/12.3026293

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available