郑州大学学报（理学版）2025，Vol.57Issue(5)：1-8,8.DOI:10.13705/j.issn.1671-6841.2024041
基于改进YOLOv7的火灾火焰检测模型
A Flame Detection Model Based on Improved YOLOv7
摘要
Abstract
The issue of inadequate effectiveness of existing object detection models for detecting flame was addressed.A novel fire detection model was proposed by optimizing and enhancing the network structure of the YOLOv7 algorithm.Several innovative improvements were introduced in three key aspects.Firstly,the YOLOv7 was augmented with a small object detection layer and SE attention,coordinate attention,and Biformer modules were incorporated to enhance the extraction of small object features.Secondly,the CoordConv and PConv modules were integrated to replace the standard convolution blocks in the network,resulting in reduced computational complexity during training and deployment,and improved network de-tection speed.Lastly,the issue of inconsistent quality of annotated bounding boxes in the experimental dataset was addressed by replacing the CIoU loss function with the Wise-IoU loss function.Experimental results conducted on the KMU Fire and Smoke database demonstrated that the improved model achieved a 2.5 percentage points increase in average precision and a 1.7 percentage points increase in recall.Addi-tionally,the frame rate reached 79.4 frames per second.This dual improvement in detection performance and speed surpassed that of traditional object detection algorithms,making the model more effective in detecting fires.关键词
YOLOv7/火灾检测/Wise-IoU损失函数/注意力机制/PConv模块Key words
YOLOv7/fire detection/Wise-IoU loss function/attention mechanism/PConv module分类
信息技术与安全科学引用本文复制引用
刘成明,吴凡,李学相..基于改进YOLOv7的火灾火焰检测模型[J].郑州大学学报（理学版）,2025,57(5):1-8,8.基金项目
国家自然科学基金项目(62006210,62206252) （62006210,62206252）
河南省重大公益专项项目(201300210500) （201300210500）
南阳市协同创新重大专项项目(22XTCX12001) （22XTCX12001）
河南省重大科技专项项目(221100210100) （221100210100）
嵩山实验室预研项目(YYJC022022001) （YYJC022022001）
嵩山实验室资助项目(232102210154) （232102210154）
