A Video-Based Fire Detection Using Deep Learning Models

Byoungjun Kim,Joonwhoan Lee

doi:10.3390/app9142862

Byoungjun Kim, Joonwhoan Lee

Open Access

https://doi.org/10.3390/app9142862

Copy DOI

Journal: Applied sciences	Publication Date: Jul 18, 2019
Citations: 118	License type: CC BY 4.0

Affiliation: Jeonbuk National University

Abstract

Fire is an abnormal event which can cause significant damage to lives and property. In this paper, we propose a deep learning-based fire detection method using a video sequence, which imitates the human fire detection process. The proposed method uses Faster Region-based Convolutional Neural Network (R-CNN) to detect the suspected regions of fire (SRoFs) and of non-fire based on their spatial features. Then, the summarized features within the bounding boxes in successive frames are accumulated by Long Short-Term Memory (LSTM) to classify whether there is a fire or not in a short-term period. The decisions for successive short-term periods are then combined in the majority voting for the final decision in a long-term period. In addition, the areas of both flame and smoke are calculated and their temporal changes are reported to interpret the dynamic fire behavior with the final fire decision. Experiments show that the proposed long-term video-based method can successfully improve the fire detection accuracy compared with the still image-based or short-term video-based method by reducing both the false detections and the misdetections.

Highlights

Fire is an abnormal event which can quickly cause significant injury and property damage [1].According to the National Fire Protection Association (NAPA), the United States fire department responded to an estimated 1,319,500 fires during 2017 [2], which resulted in 3,400 civilian fire fatalities, 14,670 civilian fire injuries, and an estimated $23 billion in direct property loss
Operations, Faster Region-based Convolutional Neural Network (R-CNN) and Long Short-Term Memory (LSTM) stages should be separately trained in the proposed method
We have proposed a deep learning-based fire detection method, called detection and temporal accumulations (DTA), which imitates the

Summary

Introduction

Researchers have been investigating computer vision-based methods combined with various types of supplementary sensors [3,4,5,6] This category of technologies gives larger surveillance coverage and offers the advantage of less human intervention with a faster response, as a fire can be confirmed without requiring a visit to the fire location, and provides detailed fire information such as location, size, and degree. Despite these advantages, some issues remain concerning the system complexity, and false detection according to diverse reasons.

Methods

Results

Conclusion