<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.2d1 20170631//EN" "JATS-journalpublishing1.dtd">
<ArticleSet>
  <Article>
    <Journal>
      <PublisherName>ijesm</PublisherName>
      <JournalTitle>International Journal of Engineering, Science and</JournalTitle>
      <PISSN>I</PISSN>
      <EISSN>S</EISSN>
      <Volume-Issue>Volume 7, Issue 2</Volume-Issue>
      <PartNumber/>
      <IssueTopic>Multidisciplinary</IssueTopic>
      <IssueLanguage>English</IssueLanguage>
      <Season>February 2018</Season>
      <SpecialIssue>N</SpecialIssue>
      <SupplementaryIssue>N</SupplementaryIssue>
      <IssueOA>Y</IssueOA>
      <PubDate>
        <Year>2018</Year>
        <Month>02</Month>
        <Day>28</Day>
      </PubDate>
      <ArticleType>Engineering, Science and Mathematics</ArticleType>
      <ArticleTitle>Fire Detection from Video based on Temporal Variation,Temporal Periodicity andSpatial Variance Analysis</ArticleTitle>
      <SubTitle/>
      <ArticleLanguage>English</ArticleLanguage>
      <ArticleOA>Y</ArticleOA>
      <FirstPage>359</FirstPage>
      <LastPage>368</LastPage>
      <AuthorList>
        <Author>
          <FirstName>Muhammad Kamal Hossen  MonazilHoqueChowdhury**</FirstName>
          <LastName>IntakhabAlamChowdhury***</LastName>
          <AuthorLanguage>English</AuthorLanguage>
          <Affiliation/>
          <CorrespondingAuthor>N</CorrespondingAuthor>
          <ORCID/>
        </Author>
      </AuthorList>
      <DOI/>
      <Abstract>Fire detection is an important issue in the modern security system. In this paper, a vision based fire detection system is proposed. The proposed method integrates both color and motion information to isolate the fire regions from the video frame. First, based on some training fire images,the color of each pixel is analyzed to locate the fire colored pixel. Temporal variation and temporal periodicity of each pixel are calculated to determine which of these fire colored pixels actually fire pixels are. Then, we analyzed the spatial variance of each fire colored region. And in this step, some spurious fire regions are eliminated. The fire has some center regions which are much brighter and relatively stationary than other regions. Extracting these regions is also a feature of this work.Finally, a region growing algorithm is applied to find the actual fire regions in the video. In the experimental result, we showed that the proposed method works in various environmental conditions and the number of false fire frames detection is very lowfor fire colored stationary or moving object.</Abstract>
      <AbstractLanguage>English</AbstractLanguage>
      <Keywords>YCbCr; Color model conversion; Standard deviation; Temporal variance; Spatial variance.</Keywords>
      <URLs>
        <Abstract>https://ijesm.co.in/ubijournal-v1copy/journals/abstract.php?article_id=4917&amp;title=Fire Detection from Video based on Temporal Variation,Temporal Periodicity andSpatial Variance Analysis</Abstract>
      </URLs>
      <References>
        <ReferencesarticleTitle>References</ReferencesarticleTitle>
        <ReferencesfirstPage>16</ReferencesfirstPage>
        <ReferenceslastPage>19</ReferenceslastPage>
        <References/>
      </References>
    </Journal>
  </Article>
</ArticleSet>