Machine Learning-Based On-Device Smoke and Flame Detection System Using Light Intensity of RGB Color Sensor
Authors:
- Minsung ParkMPMinsung Park
- Bo-Hee LeeBLBo-Hee Lee
- Haiyoung JungHJHaiyoung Jung
Open Access
- 31 December 2025
- journal article
- Published by Korea Institute of Fire Science and Engineering in International Journal of Fire Science and Engineering
- Vol. 39 (4) , 37-45
Abstract
This study proposes an edge-based real-time fire-detection system utilizing low-cost RGB sensors and TinyML technology. To overcome the high cost and maintenance limitations of existing detection methods in large indoor spaces, we propose an efficient approach that analyzes light-intensity patterns using affordable RGB sensors. Unlike simple threshold-based methods, our system applies machine learning to precisely distinguish between the complex optical patterns of smoke and flames, thus significantly enhancing detection accuracy. Designed with an on-device AI architecture, the system performs independent and rapid fire assessment on an edge device without requiring external network connectivity. Experiments conducted in a simulated fire environment confirmed the system’s feasibility and high accuracy. Spectral analysis and multisensor fusion shall be considered in future investigations to further minimize false alarms.Keywords
Funding Information
- Regional Innovation System and Education (2025-RISE-11-008-01)
- Chungbuk Regional Innovation System and Education Center
- Ministry of Education
- Chungcheongbuk-do, Republic of Korea
This publication has 7 references indexed in Scilit:
- A Study on the Performance Analysis of Fire Detection Using a Lightweight Convolutional Neural Network ModelFire Science and Engineering, 2024
- Comparative Analysis of Fire-Detection Characteristics of Si-Based RGB Color Sensors and Existing Fire-Detection SensorsFire Science and Engineering, 2024
- Enhancing Fire Detection Technology: A UV-Based System Utilizing Fourier Spectrum Analysis for Reliable and Accurate Fire DetectionApplied Sciences, 2023
- Flame detection by heat from the infrared spectrum: Optimization and sensitivity analysisFire Safety Journal, 2022
- Uncertainty Assessment-Based Active Learning for Reliable Fire Detection SystemsIEEE Access, 2022
- Video fire detection – ReviewDigital Signal Processing, 2013
- A method for spark rejection in ultraviolet flame detectorsIEEE Transactions on Industrial Electronics, 2000