现代信息科技2025，Vol.9Issue(2)：1-6,6.DOI:10.19850/j.cnki.2096-4706.2025.02.001
火焰和烟雾检测中YOLOv8的应用和改进
Application and Improvement of YOLOv8 in Flame and Smoke Detection
韩伟娟 1平翼 2杨奥林 3远京辉 2崔二强 2董新捷2
作者信息
- 1. 中原科技学院 机电工程学院,河南 郑州 450000
- 2. 河南省公安厅 信息通信处,河南 郑州 450003
- 3. 河南财经政法大学 公共管理学院,河南 郑州 450046
- 折叠
摘要
Abstract
The fire incidents seriously threaten the safety of people's lives and property,so the fire detection is extremely essential.Based on the YOLOv8 algorithm,this paper carries out the smoke and flame detection,and improves the model structure to raise accuracy.The improvements include 3 aspects of introducing the DBB module,using the Dynamic Convolution,and optimizing the loss function.The experiments demonstrate that the three kinds of improved algorithms all have a specific rise in detection accuracy,and the YOLOv8n model which uses three improvements at the same time has increased mAP50 by 3.03%and mAP50-95 by 3.37%compared to the original YOLOv8n.Compared to Faster R-CNN and other models,various performance indicators such as mAP50 and mAP50-95 have notable enhancements,and the precision of fire detection is also improved.关键词
YOLOv8/网络结构/卷积/损失函数/mAP/准确度Key words
YOLOv8/network structure/convolution/loss function/mAP/accuracy分类
信息技术与安全科学引用本文复制引用
韩伟娟,平翼,杨奥林,远京辉,崔二强,董新捷..火焰和烟雾检测中YOLOv8的应用和改进[J].现代信息科技,2025,9(2):1-6,6.
