基于ECA和YOLOv5的隧道渗水检测方法
Tunnel water leakage detection method based on ECA and YOLOv5
杨丽 1邓靖威 2段海龙 1杨晨晨2
作者信息
- 1. 天津职业技术师范大学自动化与电气工程学院,天津 300222;天津职业技术师范大学天津市信息传感与智能控制重点实验室,天津 300222
- 2. 天津职业技术师范大学自动化与电气工程学院,天津 300222
- 折叠
摘要
针对现有方法存在的隧道渗水检测精度不高和特征融合过程中信息丢失的问题,提出了一种基于有效的通道注意力(efficient channel attention,ECA)和YOLOv5的隧道渗水检测方法.该方法融合ECA注意力模块设计瓶颈结构,加强挖掘浅层特征表征的几何结构信息,充分提取水迹特征信息的同时抑制背景特征,提高水迹检测精度.在建立的隧道渗水水迹数据集上进行实验,结果表明:对比原YOLOv5模型,所提出的隧道渗水检测方法的平均精度均值提高了10%,准确率提高了17%,召回率提高了6%.实验结果验证了该方法的有效性.
Abstract
To solve the problems of low detection accuracy and information loss in feature fusion process for methods of the existing tunnel water seepage detection,a tunnel water seepage detection method based on ECA(efficient channel at tention,ECA)and YOLOv5 is proposed,which fuses the ECA attention module to design the bottleneck structure,en-hances the mining of geometric structure information with shallow feature representation,fully extracts water stain feature information while suppressing background features,and improves water stain detection accuracy.Experimental results using an established water trace data set of tunnel seepage demonstrate that the proposed method outperforms the original YOLOv5 model.Specifically,the proposed tunnel seepage detection method achieves a 10%increase in average accuracy,a 17%in-crease in accuracy rate,and a 6%increase in recall rate,validating its effectiveness in tunnel seepage detection.
关键词
隧道渗水检测/深度学习/注意力机制Key words
tunnel water seepage detection/deep learning/attention mechanism引用本文复制引用
基金项目
天津市教委科研计划项目(2022ZD036)
天津市自然科学基金资助项目(20JCZDJC00150)
出版年
2024
NETL
NSTL
万方数据