{"title":"Early Fire Detection Using Deep Learning","authors":"Akshad Jha, Saurabh Vedak, Kapil Mundada, Raj Walnuskar, Utkarsh Chopade, Anand Iyer","doi":"10.1109/aimv53313.2021.9670963","DOIUrl":null,"url":null,"abstract":"With the recent advancement in vision-based systems, as a human we can design intelligent fire detection systems which are instrumental for improving the safety efficiency as well as improving the effectiveness of the overall fire detection systems. The objective of implementing this work is that it should be capable of generating real-time information about the fire. The aim behind doing this work is to overcome the drawbacks of traditional firefighting systems. Authors have used the modern technology like deep learning, to achieve the said objective. With the use of Deep Learning fire detection system was able to classify objects of interest from frame in real time. The proposed system is having accuracy of 80% for detecting fire in given region while overcoming the false alarm generation. With this kind of accuracy given system is able to accurately inform operators with up-to-date scene information by extracting, processing, and analysing crucial information from the given frame.","PeriodicalId":135318,"journal":{"name":"2021 International Conference on Artificial Intelligence and Machine Vision (AIMV)","volume":"11 1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Artificial Intelligence and Machine Vision (AIMV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/aimv53313.2021.9670963","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4
Abstract
With the recent advancement in vision-based systems, as a human we can design intelligent fire detection systems which are instrumental for improving the safety efficiency as well as improving the effectiveness of the overall fire detection systems. The objective of implementing this work is that it should be capable of generating real-time information about the fire. The aim behind doing this work is to overcome the drawbacks of traditional firefighting systems. Authors have used the modern technology like deep learning, to achieve the said objective. With the use of Deep Learning fire detection system was able to classify objects of interest from frame in real time. The proposed system is having accuracy of 80% for detecting fire in given region while overcoming the false alarm generation. With this kind of accuracy given system is able to accurately inform operators with up-to-date scene information by extracting, processing, and analysing crucial information from the given frame.