DSS-YOLO: an improved lightweight real-time fire detection model based on YOLOv8

Abstract Fire disasters pose significant risks to human life, economic development, and social stability. The early stages of a fire, often characterized by small flames, diffuse smoke, and obstructed objects, can lead to challenges such as missed detections and poor real-time performance. To addres...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongjie Wang, Xiaoyang Fu, Zixuan Yu, Zhifeng Zeng
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-93278-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849772414100045824
author Hongjie Wang
Xiaoyang Fu
Zixuan Yu
Zhifeng Zeng
author_facet Hongjie Wang
Xiaoyang Fu
Zixuan Yu
Zhifeng Zeng
author_sort Hongjie Wang
collection DOAJ
description Abstract Fire disasters pose significant risks to human life, economic development, and social stability. The early stages of a fire, often characterized by small flames, diffuse smoke, and obstructed objects, can lead to challenges such as missed detections and poor real-time performance. To address these issues, we propose a DSS-YOLO model based on an improved YOLOv8n architecture, designed to enhance the recognition accuracy of obscured objects and small targets while reducing computational overhead. Specifically, we replace all C2f modules in the Backbone with DynamicConv modules to reduce computation without sacrificing feature extraction capabilities. We also introduce the SEAM attention mechanism to improve detection of obscured and small targets, and the SPPELAN module at the end of the Backbone to enhance detection across different scales. The model is evaluated using the public dataset mytest-hrswj, which contains diverse fire scenarios, including indoors, forests, and buildings. Compared with the original YOLOv8n, the DSS-YOLOv8 model proposed in this paper improves mAP by 0.6% and Recall by 1.6%, while reducing the model size and FLOPs by 3.4% and 12.3% respectively. The results of this study provide effective technical support for intelligent fire monitoring systems, significantly reducing the computational cost of the model. It enhances real-time fire detection capabilities in complex fire scenarios, facilitating the early detection of fire hazards and helping to minimize the damage caused by fires.
format Article
id doaj-art-28cba0eebdc44402bfc3fde98f34392d
institution DOAJ
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-28cba0eebdc44402bfc3fde98f34392d2025-08-20T03:02:19ZengNature PortfolioScientific Reports2045-23222025-03-0115111310.1038/s41598-025-93278-wDSS-YOLO: an improved lightweight real-time fire detection model based on YOLOv8Hongjie Wang0Xiaoyang Fu1Zixuan Yu2Zhifeng Zeng3School of Computer Science, Zhuhai College of Science and TechnologySchool of Computer Science, Zhuhai College of Science and TechnologySchool of Computer Science, Zhuhai College of Science and TechnologySchool of Computer Science, Zhuhai College of Science and TechnologyAbstract Fire disasters pose significant risks to human life, economic development, and social stability. The early stages of a fire, often characterized by small flames, diffuse smoke, and obstructed objects, can lead to challenges such as missed detections and poor real-time performance. To address these issues, we propose a DSS-YOLO model based on an improved YOLOv8n architecture, designed to enhance the recognition accuracy of obscured objects and small targets while reducing computational overhead. Specifically, we replace all C2f modules in the Backbone with DynamicConv modules to reduce computation without sacrificing feature extraction capabilities. We also introduce the SEAM attention mechanism to improve detection of obscured and small targets, and the SPPELAN module at the end of the Backbone to enhance detection across different scales. The model is evaluated using the public dataset mytest-hrswj, which contains diverse fire scenarios, including indoors, forests, and buildings. Compared with the original YOLOv8n, the DSS-YOLOv8 model proposed in this paper improves mAP by 0.6% and Recall by 1.6%, while reducing the model size and FLOPs by 3.4% and 12.3% respectively. The results of this study provide effective technical support for intelligent fire monitoring systems, significantly reducing the computational cost of the model. It enhances real-time fire detection capabilities in complex fire scenarios, facilitating the early detection of fire hazards and helping to minimize the damage caused by fires.https://doi.org/10.1038/s41598-025-93278-wFire detectionYOLOv8DynamicConvSEAMSPPELAN
spellingShingle Hongjie Wang
Xiaoyang Fu
Zixuan Yu
Zhifeng Zeng
DSS-YOLO: an improved lightweight real-time fire detection model based on YOLOv8
Scientific Reports
Fire detection
YOLOv8
DynamicConv
SEAM
SPPELAN
title DSS-YOLO: an improved lightweight real-time fire detection model based on YOLOv8
title_full DSS-YOLO: an improved lightweight real-time fire detection model based on YOLOv8
title_fullStr DSS-YOLO: an improved lightweight real-time fire detection model based on YOLOv8
title_full_unstemmed DSS-YOLO: an improved lightweight real-time fire detection model based on YOLOv8
title_short DSS-YOLO: an improved lightweight real-time fire detection model based on YOLOv8
title_sort dss yolo an improved lightweight real time fire detection model based on yolov8
topic Fire detection
YOLOv8
DynamicConv
SEAM
SPPELAN
url https://doi.org/10.1038/s41598-025-93278-w
work_keys_str_mv AT hongjiewang dssyoloanimprovedlightweightrealtimefiredetectionmodelbasedonyolov8
AT xiaoyangfu dssyoloanimprovedlightweightrealtimefiredetectionmodelbasedonyolov8
AT zixuanyu dssyoloanimprovedlightweightrealtimefiredetectionmodelbasedonyolov8
AT zhifengzeng dssyoloanimprovedlightweightrealtimefiredetectionmodelbasedonyolov8