Automating Fire Detection and Suppression with Computer Vision: A Multi-Layered Filtering Approach to Enhanced Fire Safety and Rapid Response

IF 2.3 3区工程技术 Q2 ENGINEERING, MULTIDISCIPLINARY

Fire Technology Pub Date : 2023-03-22 DOI:10.1007/s10694-023-01392-w

Md Safwan Mondal, Varun Prasad, Ramendra Kumar, Nilendu Saha, Saumadeep Guha, Ratna Ghosh, Achintya Mukhopadhyay, Sourav Sarkar

{"title":"Automating Fire Detection and Suppression with Computer Vision: A Multi-Layered Filtering Approach to Enhanced Fire Safety and Rapid Response","authors":"Md Safwan Mondal, Varun Prasad, Ramendra Kumar, Nilendu Saha, Saumadeep Guha, Ratna Ghosh, Achintya Mukhopadhyay, Sourav Sarkar","doi":"10.1007/s10694-023-01392-w","DOIUrl":null,"url":null,"abstract":"<div><p>A computer vision-based integrated fire detection and automated suppression device capable of real-time functioning is proposed to enhance the fire safety. The developed multilayered algorithm considers color based clue detection and thereafter incorporates three filtration stages ‘Centroid Analysis’, ‘Histogram Analysis’ and ‘Variance Analysis’ for successful fire detection. Results from the proposed algorithm has been compared and validated against standard video datasets and was found to have an overall accuracy of 95.26% with 91.61% true positive detection rate, only 8.39% of false detection in positive fire videos and true negative rate of 98.91% with only 1.09% of false detection in negative nonfire videos. Additionally, our algorithm showed an average improvement of 7.95% in accuracy and 9.43% in precision over existing algorithms, demonstrating its sensitivity and reliability for effective fire detection and suppression. The algorithm also includes unique fire localization techniques to locate the detected fire, which was integrated with an Arduino based suppression unit to provide a real- time autonomous fire suppression. Laboratory-scale experimental validation has shown practical significance of the proposed system for any kind of personal, industrial, indoor, or outdoor environmental applications with a high precision value of 99.51% and a recall value of 95.93%.\n</p></div>","PeriodicalId":558,"journal":{"name":"Fire Technology","volume":"59 4","pages":"1555 - 1583"},"PeriodicalIF":2.3000,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10694-023-01392-w.pdf","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fire Technology","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1007/s10694-023-01392-w","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 1

Abstract

A computer vision-based integrated fire detection and automated suppression device capable of real-time functioning is proposed to enhance the fire safety. The developed multilayered algorithm considers color based clue detection and thereafter incorporates three filtration stages ‘Centroid Analysis’, ‘Histogram Analysis’ and ‘Variance Analysis’ for successful fire detection. Results from the proposed algorithm has been compared and validated against standard video datasets and was found to have an overall accuracy of 95.26% with 91.61% true positive detection rate, only 8.39% of false detection in positive fire videos and true negative rate of 98.91% with only 1.09% of false detection in negative nonfire videos. Additionally, our algorithm showed an average improvement of 7.95% in accuracy and 9.43% in precision over existing algorithms, demonstrating its sensitivity and reliability for effective fire detection and suppression. The algorithm also includes unique fire localization techniques to locate the detected fire, which was integrated with an Arduino based suppression unit to provide a real- time autonomous fire suppression. Laboratory-scale experimental validation has shown practical significance of the proposed system for any kind of personal, industrial, indoor, or outdoor environmental applications with a high precision value of 99.51% and a recall value of 95.93%.

Abstract Image

查看原文本刊更多论文

基于计算机视觉的火灾自动探测与灭火:一种多层过滤方法以提高火灾安全和快速反应

为提高火灾安全，提出了一种基于计算机视觉的实时火灾探测与自动灭火综合装置。开发的多层算法考虑基于颜色的线索检测，然后结合三个过滤阶段“质心分析”，“直方图分析”和“方差分析”，以成功检测火灾。通过与标准视频数据集的对比和验证，发现该算法的总体准确率为95.26%，真阳性检出率为91.61%，阳性火灾视频的真阴性检出率为8.39%，阴性非火灾视频的真阴性检出率为98.91%，假检率为1.09%。与现有算法相比，该算法的准确率平均提高了7.95%，精密度平均提高了9.43%，证明了该算法对有效火灾探测和灭火的灵敏度和可靠性。该算法还包括独特的火灾定位技术来定位检测到的火灾，该技术与基于Arduino的灭火单元集成在一起，提供实时自主灭火。实验室规模的实验验证表明，该系统对任何类型的个人，工业，室内或室外环境应用具有实际意义，精度值高达99.51%，召回值为95.93%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Fire Technology 工程技术-材料科学：综合

CiteScore

6.60

自引率

14.70%

发文量

137

审稿时长

7.5 months

期刊介绍： Fire Technology publishes original contributions, both theoretical and empirical, that contribute to the solution of problems in fire safety science and engineering. It is the leading journal in the field, publishing applied research dealing with the full range of actual and potential fire hazards facing humans and the environment. It covers the entire domain of fire safety science and engineering problems relevant in industrial, operational, cultural, and environmental applications, including modeling, testing, detection, suppression, human behavior, wildfires, structures, and risk analysis. The aim of Fire Technology is to push forward the frontiers of knowledge and technology by encouraging interdisciplinary communication of significant technical developments in fire protection and subjects of scientific interest to the fire protection community at large. It is published in conjunction with the National Fire Protection Association (NFPA) and the Society of Fire Protection Engineers (SFPE). The mission of NFPA is to help save lives and reduce loss with information, knowledge, and passion. The mission of SFPE is advancing the science and practice of fire protection engineering internationally.