Title: Real-time long short-term glance-based fire detection using a CNN-LSTM neural network

Authors: Huan Van Nguyen; Thang Xuan Pham; Cuong Nguyen Le

Addresses: Faculty of Information Technology, Nguyen Tat Thanh University, Ho Chi Minh City, Vietnam ' Faculty of Electronics and Telecommunication, Electric Power of University, Hanoi, Vietnam ' Faculty of Electronics and Telecommunication, Electric Power of University, Hanoi, Vietnam

Abstract: Vision-based fire detection is widely studied recently to reduce the damage of fire disaster thanks to the advantages of software-based methods comparing to traditional hardware-based fire detection using sensors. This paper presents a novel method for fire detection using the convolutional neural networks on image sequences of videos to extract both the spatial and temporal information for fire classification. The system includes a CNN network to extract the image features, and short-term and long-term stages at the end for classification. Experiments carried out on the common public datasets show promising results in terms of performance in comparison to the previous works.

Keywords: fire detection; long short-term memory; LSTM; temporal CNN.

DOI: 10.1504/IJIIDS.2021.118545

International Journal of Intelligent Information and Database Systems, 2021 Vol.14 No.4, pp.349 - 364

Received: 03 Jul 2020
Accepted: 13 Oct 2020
Published online: 28 Oct 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article