Journal
IEEE ACCESS
Volume 9, Issue -, Pages 146667-146679Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3122346
Keywords
Image color analysis; Feature extraction; Machine learning algorithms; Deep learning; Computer architecture; Microprocessors; Heuristic algorithms; Fire detection; convolutional neural network; ImageNet; long short-term memory
Categories
Funding
- National Research Foundation of Korea (NRF) - Ministry of Education [NRF2018R1D1A1B07049146]
- Vingroup Joint Stock Company
- Domestic Master/Ph.D. Scholarship Programme of Vingroup Innovation Foundation (VINIF), Vingroup Big Data Institute (VINBIGDATA) [VINIF.2020.TS.103]
Ask authors/readers for more resources
The paper proposes a multistage fire detection method using convolutional neural networks (CNNs) and long short-term memory (LSTM) networks, combining early detection of fire candidates and 2D features extraction to determine if it is a true fire, showing competitive performance in real-world applications.
Fire is one of the most commonly occurring disasters and is the main cause of catastrophic personal injury and devastating property damage. An early detection system is necessary to prevent fires from spreading out of control. In this paper, we propose a multistage fire detection method using convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. In the first stage, fire candidates are detected by using their salient features, such as their color, flickering frequency, and brightness. In the second stage, a pretrained CNN model is used to extract the 2D features of flames that are the input for the LSTM network. In the last stage, a softmax classifier is utilized to determine whether the flames represent a true fire or a nonfire moving object. The experimental results show that our proposed method can achieve competitive performance compared with other state-of-the-art methods and is suitable for real-world applications.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available