利用基于注意力的深度语义分割进行火/火焰检测

IF 1.5 4区 工程技术 Q3 ENGINEERING, ELECTRICAL & ELECTRONIC
Anil Aliser, Zeynep Bala Duranay
{"title":"利用基于注意力的深度语义分割进行火/火焰检测","authors":"Anil Aliser, Zeynep Bala Duranay","doi":"10.1007/s40998-024-00697-y","DOIUrl":null,"url":null,"abstract":"<p>Fire/flame detection from images or videos is very important for early fire warning systems. In this way, fires can be intervened early and extinguished before they grow. Recently, many studies have been published on early fire warning systems based on image processing and machine learning. These studies are generally color space-based image segmentation applications. The given images are first transferred to another color space, and the fire/flame regions are determined by using color segmentation. In this study, a segmentation technique using deep network architecture for fire/flame detection is presented. The proposed method is a segmentation network structure in which the attention gate module is integrated. In the presented method, the success of the deep network architecture is evaluated by using the dice, Tversky, and focal Tversky loss functions. A data set containing 500 images was used for experimental studies, with the fivefold cross-validation criterion, and the success achieved was presented depending on the mean dice and Jaccard similarity criteria. The calculated results were compared with some studies in the literature. The comparison results were shown that the presented technique produced more successful results.</p>","PeriodicalId":49064,"journal":{"name":"Iranian Journal of Science and Technology-Transactions of Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":1.5000,"publicationDate":"2024-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Fire/Flame Detection with Attention-Based Deep Semantic Segmentation\",\"authors\":\"Anil Aliser, Zeynep Bala Duranay\",\"doi\":\"10.1007/s40998-024-00697-y\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Fire/flame detection from images or videos is very important for early fire warning systems. In this way, fires can be intervened early and extinguished before they grow. Recently, many studies have been published on early fire warning systems based on image processing and machine learning. These studies are generally color space-based image segmentation applications. The given images are first transferred to another color space, and the fire/flame regions are determined by using color segmentation. In this study, a segmentation technique using deep network architecture for fire/flame detection is presented. The proposed method is a segmentation network structure in which the attention gate module is integrated. In the presented method, the success of the deep network architecture is evaluated by using the dice, Tversky, and focal Tversky loss functions. A data set containing 500 images was used for experimental studies, with the fivefold cross-validation criterion, and the success achieved was presented depending on the mean dice and Jaccard similarity criteria. The calculated results were compared with some studies in the literature. The comparison results were shown that the presented technique produced more successful results.</p>\",\"PeriodicalId\":49064,\"journal\":{\"name\":\"Iranian Journal of Science and Technology-Transactions of Electrical Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2024-02-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Iranian Journal of Science and Technology-Transactions of Electrical Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s40998-024-00697-y\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Iranian Journal of Science and Technology-Transactions of Electrical Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s40998-024-00697-y","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

摘要

对于早期火灾预警系统来说,从图像或视频中探测火情/火焰非常重要。通过这种方式,可以在火灾扩大之前及早干预和扑灭。最近,许多关于基于图像处理和机器学习的早期火灾预警系统的研究都已发表。这些研究一般都是基于色彩空间的图像分割应用。首先将给定图像转换到另一个色彩空间,然后通过色彩分割确定火/火焰区域。本研究提出了一种利用深度网络架构进行火灾/火焰检测的分割技术。所提出的方法是一种分割网络结构,其中集成了注意力门模块。在所提出的方法中,通过使用骰子、Tversky 和 focal Tversky 损失函数来评估深度网络架构的成功与否。实验研究使用了包含 500 幅图像的数据集,采用五倍交叉验证标准,并根据骰子平均值和 Jaccard 相似度标准对所取得的成功进行了评估。计算结果与文献中的一些研究进行了比较。比较结果表明,所提出的技术产生了更成功的结果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Fire/Flame Detection with Attention-Based Deep Semantic Segmentation

Fire/Flame Detection with Attention-Based Deep Semantic Segmentation

Fire/flame detection from images or videos is very important for early fire warning systems. In this way, fires can be intervened early and extinguished before they grow. Recently, many studies have been published on early fire warning systems based on image processing and machine learning. These studies are generally color space-based image segmentation applications. The given images are first transferred to another color space, and the fire/flame regions are determined by using color segmentation. In this study, a segmentation technique using deep network architecture for fire/flame detection is presented. The proposed method is a segmentation network structure in which the attention gate module is integrated. In the presented method, the success of the deep network architecture is evaluated by using the dice, Tversky, and focal Tversky loss functions. A data set containing 500 images was used for experimental studies, with the fivefold cross-validation criterion, and the success achieved was presented depending on the mean dice and Jaccard similarity criteria. The calculated results were compared with some studies in the literature. The comparison results were shown that the presented technique produced more successful results.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
5.50
自引率
4.20%
发文量
93
审稿时长
>12 weeks
期刊介绍: Transactions of Electrical Engineering is to foster the growth of scientific research in all branches of electrical engineering and its related grounds and to provide a medium by means of which the fruits of these researches may be brought to the attentionof the world’s scientific communities. The journal has the focus on the frontier topics in the theoretical, mathematical, numerical, experimental and scientific developments in electrical engineering as well as applications of established techniques to new domains in various electical engineering disciplines such as: Bio electric, Bio mechanics, Bio instrument, Microwaves, Wave Propagation, Communication Theory, Channel Estimation, radar & sonar system, Signal Processing, image processing, Artificial Neural Networks, Data Mining and Machine Learning, Fuzzy Logic and Systems, Fuzzy Control, Optimal & Robust ControlNavigation & Estimation Theory, Power Electronics & Drives, Power Generation & Management The editors will welcome papers from all professors and researchers from universities, research centers, organizations, companies and industries from all over the world in the hope that this will advance the scientific standards of the journal and provide a channel of communication between Iranian Scholars and their colleague in other parts of the world.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信