TBU Publications
Repository of TBU Publications

Fire detection in video stream by using simple artificial neural network

DSpace Repository

Show simple item record


dc.title Fire detection in video stream by using simple artificial neural network en
dc.contributor.author Janků, Peter
dc.contributor.author Komínková Oplatková, Zuzana
dc.contributor.author Dulík, Tomáš
dc.contributor.author Snopek, Petr
dc.contributor.author Líba, Jiří
dc.relation.ispartof Mendel
dc.identifier.issn 1803-3814 Scopus Sources, Sherpa/RoMEO, JCR
dc.date.issued 2018
utb.relation.volume 24
utb.relation.issue 2
dc.citation.spage 55
dc.citation.epage 60
dc.type article
dc.language.iso en
dc.publisher Brno University of Technology
dc.identifier.doi 10.13164/mendel.2018.2.055
dc.relation.uri https://mendel-journal.org/index.php/mendel/article/view/12
dc.subject Artificial neural networks en
dc.subject Computer vision en
dc.subject Fire detection en
dc.description.abstract This paper deals with the preliminary research of the fire detection in a video stream. Early fire detection can save lives and properties from huge losses and damages. Therefore the surveillance of the areas is necessary. Early fire discovery with high accuracy, i.e. a low number of false positive or false negative cases, is essential in any environment, especially in places with the high motion of people. The traditional fire detection sensors have some drawbacks: they need separate systems and infrastructure to be implemented, to use sensors in the case of the industrial environment with open fire technologies is often impossible, and others. The fire detection in a video stream is one of the possible and feasible solutions suitable for replacement or supplement of conventional fire detection sensors without a need for installation a huge infrastructure. The paper provides the state of the art in the fire detection. The following part of the paper proposes the new system of feature extraction and describes the feedforward neural network which was used for the training and testing of the proposed idea. The promising results are presented with over 93% accuracy on a selected dataset of movies which consist of more and highly varied instances than published by other researchers involved in the fire detection field. The structure of the neural networks promises higher computational speed than currently implemented deep learning systems. © 2018, Brno University of Technology. All rights reserved. en
utb.faculty Faculty of Applied Informatics
dc.identifier.uri http://hdl.handle.net/10563/1009087
utb.identifier.obdid 43879000
utb.identifier.scopus 2-s2.0-85067653095
utb.source j-scopus
dc.date.accessioned 2019-09-19T07:56:15Z
dc.date.available 2019-09-19T07:56:15Z
dc.rights Attribution-NonCommercial-ShareAlike 4.0 International
dc.rights.uri https://creativecommons.org/licenses/by-nc-sa/4.0/
dc.rights.access openAccess
utb.ou CEBIA-Tech
utb.contributor.internalauthor Janků, Peter
utb.contributor.internalauthor Komínková Oplatková, Zuzana
utb.contributor.internalauthor Dulík, Tomáš
utb.fulltext.sponsorship This work was supported by Technology Agency of the Czech Republic (TAČR) within the Visual Computing Competence Center - V3C project No. TE01020415, further by the Ministry of Education, Youth and Sports of the Czech Republic within the National Sustainability Programme Project no. LO1303 (MSMT-7778/2014) and by the European Regional Development
utb.scopus.affiliation Tomas Bata University in Zlin, Faculty of Applied Informatics Nam, T.G. Masaryka 5555, Zlin, 760 01, Czech Republic; UNIS a.s, Jundrovska 33, Brno, 624 00, Czech Republic
utb.fulltext.projects TE01020415
utb.fulltext.projects LO1303
utb.fulltext.projects MSMT-7778/2014
utb.fulltext.projects CZ.1.05/2.1.00/03.0089
utb.fulltext.projects IC1406
Find Full text

Files in this item

Show simple item record

Attribution-NonCommercial-ShareAlike 4.0 International Except where otherwise noted, this item's license is described as Attribution-NonCommercial-ShareAlike 4.0 International