首页|基于改进HRNetV2的高寒区隧道衬砌冻害检测方法

基于改进HRNetV2的高寒区隧道衬砌冻害检测方法

扫码查看
针对修建在高寒区的隧道衬砌存在的所处环境恶劣、冻害频发、衬砌图像干扰因素多、冻害目标尺度不一致及传统人工目视检测方法效率低下且成本昂贵等问题,提出了基于HRNetV2的高寒区隧道衬砌冻害检测方法.首先以HRNetV2为基础模型,提出改进模型,在主干特征提取网络结合迁移学习的知识,在结构中引入注意力机制以加强模型对于冻害特征的学习能力,并使用Focalloss作为损失函数以解决类别不平衡问题.为验证改进后模型的性能,使用高清摄像头采集高寒区隧道衬砌冻害图像,经过裁剪及数据增强等手段,建立一个包含2 800张图像的冻害数据集.实验结果表明,改进后的模型在冻害数据集上的平均交并比(mean intersection over union,mloU)可达到89.05%,相比原始模型提升了 5.41%,在面对复杂形态冻害时展现出较好的鲁棒性,可直接应用于高分辨率原图;且在综合性能上优于DeeplabV3+、U-Net、PSPNet三种模型.所提方法可准确、安全地实现衬砌冻害智能检测,可为高寒区隧道智能化运维提供一定技术支持.
Freezing Damage Detection Method of Tunnel Lining in Cold Regions Based on Improved HRNetV2
Aiming at the problems of harsh environment,frequent frost damage,multiple interference factors in lining images,in-consistent scale of frost damage targets,and low efficiency and high cost of traditional manual visual inspection methods for tunnel lin-ing built in cold regions,a frost damage detection method for tunnel lining in cold regions based on HRNetV2 was proposed.Firstly,based on HRNetV2,an improved model was proposed,which combines the knowledge of transfer learning in the backbone feature ex-traction network,introduces attention mechanism in the structure to enhance the model's learning ability for frost damage features,and uses Focalloss as the loss function to solve the problem of class imbalance.In order to verify the performance of the improved model,frozen damage images of tunnel lining in cold regions were collected by high-definition cameras.After clipping and data enhancement,a semantic segmentation dataset containing 2 800 cracks,spalling and ice hanging was established.The experimental results show that the mean intersection over union(mIoU)of the improved model can reach 89.05%on the freezing damage dataset,which is 5.41%higher than that of the original model,showing good robustness in the face of complex forms of frost damage,and can be directly ap-plied to high-resolution original images.Compared with DeeplabV3+,U-Net and PSPNet three classical semantic segmentation mod-els,the improved HRNetV2 model has more advantages in comprehensive performance.The proposed method can accurately and safely achieve intelligent detection of lining frost damage,providing certain technical support for intelligent operation and maintenance of tun-nels in cold regions.

highway tunnellining freezing damage detectiontheoretical analysissemantic segmentationattention mechanism

郭强、车博文、包卫星、潘振华、卢汉青

展开 >

长安大学公路学院,西安 710064

新疆交通建设管理局,乌鲁木齐 830002

公路隧道 衬砌冻害检测 理论分析 语义分割 注意力机制

新疆维吾尔自治区重大科技专项陕西省自然科学基础研究计划面上项目中央高校基本科研业务费资助项目(领军人才计划)

2020A03003-72021JM-180300102211302

2024

科学技术与工程
中国技术经济学会

科学技术与工程

CSTPCD北大核心
影响因子:0.338
ISSN:1671-1815
年,卷(期):2024.24(25)