Affiliation:
1. School of Mechanical Engineering, Gwangju Institute of Science and Technology, Gwangju 61005, South Korea
Abstract
Abstract
This paper proposes a video-based SlowFast model that combines the SlowFast deep learning model with a new boundary box annotation algorithm. The new algorithm, namely the MTB (i.e., the ratio of the number of Moving object pixels To the number of Bounding box pixels) algorithm, is devised to automatically annotate the bounding box that includes the smoke with fuzzy boundaries. The model parameters of the MTB algorithm are examined by multifactor analysis of variance. To demonstrate the validity of the proposed approach, a case study is provided that examines real video clips of incipient forest fires with small amounts of smoke. The performance of the proposed approach is compared with those of existing deep learning models, including convolutional neural network (CNN), faster region-based CNN (faster R-CNN), and SlowFast. It is demonstrated that the proposed approach achieves enhanced detection accuracy, while reducing false negative rates.
Funder
National Research Foundation of Korea
MSIT
Publisher
Oxford University Press (OUP)
Subject
Computational Mathematics,Computer Graphics and Computer-Aided Design,Human-Computer Interaction,Engineering (miscellaneous),Modeling and Simulation,Computational Mechanics
Reference52 articles.
1. A review on forest fire detection techniques;Alkhatib;International Journal of Distributed Sensor Networks,2014
2. Object detection in sports videos;Burić,2018
3. Object-based change detection;Chen;International Journal of Remote Sensing,2012
4. Dynamic analysis for video based smoke detection;Chen;International Journal of Computer Science Issues,2013
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献