A multi-object detection method for building fire warnings through artificial intelligence generated content

Abstract Timely fire warnings are crucial for minimizing casualties during building fires. In this paper, a multi-object detection method through artificial intelligence generated content (AIGC) is proposed to improve building fire warning capability. First, an AIGC workflow of dataset construction...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingwei Fu, Zhen Xu, Qingrui Yue, Jiarui Lin, Ning Zhang, Yujie Zhao, Donglian Gu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-02865-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849705051434516480
author Jingwei Fu
Zhen Xu
Qingrui Yue
Jiarui Lin
Ning Zhang
Yujie Zhao
Donglian Gu
author_facet Jingwei Fu
Zhen Xu
Qingrui Yue
Jiarui Lin
Ning Zhang
Yujie Zhao
Donglian Gu
author_sort Jingwei Fu
collection DOAJ
description Abstract Timely fire warnings are crucial for minimizing casualties during building fires. In this paper, a multi-object detection method through artificial intelligence generated content (AIGC) is proposed to improve building fire warning capability. First, an AIGC workflow of dataset construction on building fire images is designed, to overcome the limitation due to a serious lack of real building fire images. Validation experiments demonstrate that the detection accuracy of the model trained on the AIGC dataset is only 1.6% lower than that of the model trained on the real image dataset. Subsequently, a multi-object detection model is developed to enhance its feature capture capability, by incorporating the MLCA mechanism into its backbone and replacing the feature fusion layer in its neck. The developed model can detect the flame and smoke of building fires with an accuracy of 95.7%. Finally, the case study involving three real fire incidents demonstrates that the proposed method can detect fires within 2s since the fire starting, which achieves an improvement of at least 6.5 times in the fire warning efficiency compared to the traditional fire alarms. Therefore, the proposed method can deliver timely fire warnings for the evacuation and rescue efforts during building fires.
format Article
id doaj-art-c35f0c56cc1945cbb7ed7f227706916d
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-c35f0c56cc1945cbb7ed7f227706916d2025-08-20T03:16:34ZengNature PortfolioScientific Reports2045-23222025-05-0115111310.1038/s41598-025-02865-4A multi-object detection method for building fire warnings through artificial intelligence generated contentJingwei Fu0Zhen Xu1Qingrui Yue2Jiarui Lin3Ning Zhang4Yujie Zhao5Donglian Gu6Research Institute of Urbanization and Urban Safety, School of Future Cities, University of Science and Technology BeijingResearch Institute of Urbanization and Urban Safety, School of Future Cities, University of Science and Technology BeijingResearch Institute of Urbanization and Urban Safety, School of Future Cities, University of Science and Technology BeijingDepartment of Civil Engineering, Tsinghua UniversityResearch Institute of Urbanization and Urban Safety, School of Future Cities, University of Science and Technology BeijingResearch Institute of Urbanization and Urban Safety, School of Future Cities, University of Science and Technology BeijingResearch Institute of Urbanization and Urban Safety, School of Future Cities, University of Science and Technology BeijingAbstract Timely fire warnings are crucial for minimizing casualties during building fires. In this paper, a multi-object detection method through artificial intelligence generated content (AIGC) is proposed to improve building fire warning capability. First, an AIGC workflow of dataset construction on building fire images is designed, to overcome the limitation due to a serious lack of real building fire images. Validation experiments demonstrate that the detection accuracy of the model trained on the AIGC dataset is only 1.6% lower than that of the model trained on the real image dataset. Subsequently, a multi-object detection model is developed to enhance its feature capture capability, by incorporating the MLCA mechanism into its backbone and replacing the feature fusion layer in its neck. The developed model can detect the flame and smoke of building fires with an accuracy of 95.7%. Finally, the case study involving three real fire incidents demonstrates that the proposed method can detect fires within 2s since the fire starting, which achieves an improvement of at least 6.5 times in the fire warning efficiency compared to the traditional fire alarms. Therefore, the proposed method can deliver timely fire warnings for the evacuation and rescue efforts during building fires.https://doi.org/10.1038/s41598-025-02865-4
spellingShingle Jingwei Fu
Zhen Xu
Qingrui Yue
Jiarui Lin
Ning Zhang
Yujie Zhao
Donglian Gu
A multi-object detection method for building fire warnings through artificial intelligence generated content
Scientific Reports
title A multi-object detection method for building fire warnings through artificial intelligence generated content
title_full A multi-object detection method for building fire warnings through artificial intelligence generated content
title_fullStr A multi-object detection method for building fire warnings through artificial intelligence generated content
title_full_unstemmed A multi-object detection method for building fire warnings through artificial intelligence generated content
title_short A multi-object detection method for building fire warnings through artificial intelligence generated content
title_sort multi object detection method for building fire warnings through artificial intelligence generated content
url https://doi.org/10.1038/s41598-025-02865-4
work_keys_str_mv AT jingweifu amultiobjectdetectionmethodforbuildingfirewarningsthroughartificialintelligencegeneratedcontent
AT zhenxu amultiobjectdetectionmethodforbuildingfirewarningsthroughartificialintelligencegeneratedcontent
AT qingruiyue amultiobjectdetectionmethodforbuildingfirewarningsthroughartificialintelligencegeneratedcontent
AT jiaruilin amultiobjectdetectionmethodforbuildingfirewarningsthroughartificialintelligencegeneratedcontent
AT ningzhang amultiobjectdetectionmethodforbuildingfirewarningsthroughartificialintelligencegeneratedcontent
AT yujiezhao amultiobjectdetectionmethodforbuildingfirewarningsthroughartificialintelligencegeneratedcontent
AT dongliangu amultiobjectdetectionmethodforbuildingfirewarningsthroughartificialintelligencegeneratedcontent
AT jingweifu multiobjectdetectionmethodforbuildingfirewarningsthroughartificialintelligencegeneratedcontent
AT zhenxu multiobjectdetectionmethodforbuildingfirewarningsthroughartificialintelligencegeneratedcontent
AT qingruiyue multiobjectdetectionmethodforbuildingfirewarningsthroughartificialintelligencegeneratedcontent
AT jiaruilin multiobjectdetectionmethodforbuildingfirewarningsthroughartificialintelligencegeneratedcontent
AT ningzhang multiobjectdetectionmethodforbuildingfirewarningsthroughartificialintelligencegeneratedcontent
AT yujiezhao multiobjectdetectionmethodforbuildingfirewarningsthroughartificialintelligencegeneratedcontent
AT dongliangu multiobjectdetectionmethodforbuildingfirewarningsthroughartificialintelligencegeneratedcontent