FB-YOLOv8s: A fire detection algorithm based on YOLOv8s

The significance of fire detection lies in protecting public safety and safeguarding the lives and property of people. However, there exist some problems in traditional detection algorithms of fire, such as low accuracy, high miss rate, and low detection rate of small targets. To effectively solve t...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuhang Liu, Chunjuan Bo, Chong Feng
Format: Article
Language:English
Published: KeAi Communications Co. Ltd. 2025-01-01
Series:Cognitive Robotics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2667241325000163
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850117739733057536
author Yuhang Liu
Chunjuan Bo
Chong Feng
author_facet Yuhang Liu
Chunjuan Bo
Chong Feng
author_sort Yuhang Liu
collection DOAJ
description The significance of fire detection lies in protecting public safety and safeguarding the lives and property of people. However, there exist some problems in traditional detection algorithms of fire, such as low accuracy, high miss rate, and low detection rate of small targets. To effectively solve these issues, a fire detection algorithm based on YOLOv8s is introduced in this paper, called FB-YOLOv8s. First, the FasterNet lightweight network is introduced into the YOLOv8s network, merging the FasterNet Block structure of FasterNet with the original C2f modules to reduce the number of model parameters. Second, the Bi-directional Feature Pyramid Network (BiFPN) is incorporated to replace the Path Aggregation Network (PANet) in the neck network to enhance the model’s feature fusion capability. Finally, we adopt the WIoUv3 loss function to optimize the training process and improve detection accuracy. The experimental results demonstrate that compared to the original algorithm, the mAP0.5 of FB-YOLOv8s increases by 2.0 %, and the number of parameters decreases by 25.23 %. This method has better detection performance for fire targets.
format Article
id doaj-art-2dacc28da47544c8985fa0efd0253676
institution OA Journals
issn 2667-2413
language English
publishDate 2025-01-01
publisher KeAi Communications Co. Ltd.
record_format Article
series Cognitive Robotics
spelling doaj-art-2dacc28da47544c8985fa0efd02536762025-08-20T02:36:02ZengKeAi Communications Co. Ltd.Cognitive Robotics2667-24132025-01-01524024810.1016/j.cogr.2025.06.002FB-YOLOv8s: A fire detection algorithm based on YOLOv8sYuhang Liu0Chunjuan Bo1Chong Feng2School of Information and Communication Engineering, Dalian Minzu University, ChinaCorresponding author.; School of Information and Communication Engineering, Dalian Minzu University, ChinaSchool of Information and Communication Engineering, Dalian Minzu University, ChinaThe significance of fire detection lies in protecting public safety and safeguarding the lives and property of people. However, there exist some problems in traditional detection algorithms of fire, such as low accuracy, high miss rate, and low detection rate of small targets. To effectively solve these issues, a fire detection algorithm based on YOLOv8s is introduced in this paper, called FB-YOLOv8s. First, the FasterNet lightweight network is introduced into the YOLOv8s network, merging the FasterNet Block structure of FasterNet with the original C2f modules to reduce the number of model parameters. Second, the Bi-directional Feature Pyramid Network (BiFPN) is incorporated to replace the Path Aggregation Network (PANet) in the neck network to enhance the model’s feature fusion capability. Finally, we adopt the WIoUv3 loss function to optimize the training process and improve detection accuracy. The experimental results demonstrate that compared to the original algorithm, the mAP0.5 of FB-YOLOv8s increases by 2.0 %, and the number of parameters decreases by 25.23 %. This method has better detection performance for fire targets.http://www.sciencedirect.com/science/article/pii/S2667241325000163Fire detectionFB-YOLOv8sBiFPNWIoUv3
spellingShingle Yuhang Liu
Chunjuan Bo
Chong Feng
FB-YOLOv8s: A fire detection algorithm based on YOLOv8s
Cognitive Robotics
Fire detection
FB-YOLOv8s
BiFPN
WIoUv3
title FB-YOLOv8s: A fire detection algorithm based on YOLOv8s
title_full FB-YOLOv8s: A fire detection algorithm based on YOLOv8s
title_fullStr FB-YOLOv8s: A fire detection algorithm based on YOLOv8s
title_full_unstemmed FB-YOLOv8s: A fire detection algorithm based on YOLOv8s
title_short FB-YOLOv8s: A fire detection algorithm based on YOLOv8s
title_sort fb yolov8s a fire detection algorithm based on yolov8s
topic Fire detection
FB-YOLOv8s
BiFPN
WIoUv3
url http://www.sciencedirect.com/science/article/pii/S2667241325000163
work_keys_str_mv AT yuhangliu fbyolov8safiredetectionalgorithmbasedonyolov8s
AT chunjuanbo fbyolov8safiredetectionalgorithmbasedonyolov8s
AT chongfeng fbyolov8safiredetectionalgorithmbasedonyolov8s