Application and Education Training of Ship Fire Identification Emergency System based on YOLOv10
Abstract
Ship fire is a major safety hazard, and the traditional fire detection method faces many challenges in the ship environment. In this
paper, we propose a ship fire identification emergency system based on YOLOv10 model, aiming to improve the real-time and accuracy of fire
identification through effective target detection technology. YOLOv10 Has superior performance in ship fire identification, which can quickly
and accurately detect flames with limited computing resources, and is combined with existing ship emergency response systems. In addition,
this study explored the application of YOLOv10 in crew fire safety education to help improve emergency response through simulation training. The experimental results show that the system effectively improves the efficiency of ship fire warning and emergency treatment.
paper, we propose a ship fire identification emergency system based on YOLOv10 model, aiming to improve the real-time and accuracy of fire
identification through effective target detection technology. YOLOv10 Has superior performance in ship fire identification, which can quickly
and accurately detect flames with limited computing resources, and is combined with existing ship emergency response systems. In addition,
this study explored the application of YOLOv10 in crew fire safety education to help improve emergency response through simulation training. The experimental results show that the system effectively improves the efficiency of ship fire warning and emergency treatment.
Keywords
YOLOv10 Ship fire identification; Emergency response; Crew training; Fire warning
Full Text:
PDFReferences
[1] Liu Yichen, Zhang Bin, Wang Xuegui, et al. Research on real-time ship fire detection algorithm based on lightweight CNN. Fire Protection Science and Technology, 2023, 42 (1): 42-46.
[2] Shen Jing Zeng Qing elegant Nan Deng Nankun. Vehicle and pedestrian detection methods based on the YOLOv10s [J].2024.
[3] Shi Xurui. Based on deep learning [D]. Zhejiang University, 2022.
[4] Huang Yihao. Research on forest flame object recognition technology based on binocular vision [D]. The Civil Aviation Flight Academy
of China, 2024. DOI:10.27722/d.cnki.gzgmh. 2024.000099.
DOI: http://dx.doi.org/10.70711/neet.v2i9.5691
Refbacks
- There are currently no refbacks.
