DEVELOPMENT OF AN EARLY FIRE AND SMOKE DETECTION SYSTEM USING RASPBERRY PI AND MULTIMODAL ARTIFICIAL INTELLIGENCE
DOI:
https://doi.org/10.5281/Keywords:
fire detection, smoke, Raspberry Pi, artificial intelligence, YOLOv8, multimodal sensors, neural networks, IoT, MQ-2, open flame.Abstract
This paper investigates the development of an early fire and smoke detection system based on the Raspberry Pi microcomputer and multimodal artificial intelligence technologies. The system is based on the simultaneous processing of visual data video stream via Raspberry Pi Camera Module and chemical indicators . YOLOv8 and MobileNet-SSD neural networks are applied for image analysis, while a weighted decision-making algorithm is used for sensor data evaluation. The research results demonstrate that combining two channels allows fire detection in less than 1.8 seconds on average with 96.4% accuracy, which is 4–6 times faster than traditional signaling systems. Remote real-time notification capabilities via IoT platforms are also discussed.
References
1. Redmon J., Farhadi A. YOLOv3: An Incremental Improvement. arXiv preprint arXiv:1804.02767, 2018.
2. Jocher G. et al. Ultralytics YOLOv8. GitHub repository, 2023. URL: https://github.com/ultralytics/ultralytics
3. Howard A. G. et al. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv:1704.04861, 2017.
4. Muhammad K., Ahmad J., Baik S. W. Early fire detection using convolutional neural networks during surveillance for effective disaster management. Neurocomputing, 2018.
5. Raspberry Pi Foundation. Raspberry Pi 4 Model B Documentation. Cambridge, UK, 2023. URL: https://www.raspberrypi.com/documentation/
6. Hanqing W., Yong C. Fire detection with image processing and deep learning: A comprehensive review. Journal of Building Engineering, 2022.
7. MQ-2 Gas Sensor Datasheet. Hanwei Electronics Co., Ltd., 2022.
8. MQ-7 Carbon Monoxide Sensor Datasheet. SparkFun Electronics, 2021.
9. DHT22 Humidity and Temperature Sensor Datasheet. Aosong Electronics, 2022.
10. Giyosov U. Sh. Fundamentals of Semiconductor Technologies and Microprocessor System Design. Tashkent, 2024.
11. Sandler M. et al. MobileNetV2: Inverted Residuals and Linear Bottlenecks. IEEE/CVF CVPR, 2018.
12. Foggia P., Saggese A., Vento M. Real-time fire detection for video surveillance applications using a combination of experts based on color, shape and movement. IEEE Transactions on Circuits and Systems for Video Technology, 2015.
