基于深度学习的隧道超高分辨率图像病害检测框架

doi:10.13474/j.cnki.11-2246.2025.0318

摘要/Abstract

摘要： 现有隧道检测技术采集的数据通常会获得超高分辨率图像,而隧道中病害的实际面积较小,使得图像经过简单预处理(如缩放)后会发生病害信息丢失,且在有限的计算资源下训练的深度学习模型可能会出现物体检测率降低、训练不稳定等现象。针对上述问题,本文提出了一种基于深度学习和隧道超高分辨率图像的病害检测框架,通过对超高分辨率图像进行预处理,将原始图像分割成更小的补丁图像,将超高分辨率图像调整到合适的大小,以提高检测模型的性能,该框架适用于任何深度学习模型。试验结果表明,相较于常规检测流程,本文所提框架下的模型性能提高了约77.19%;且该框架适用于一般的超高分辨率图像,可以有效识别隧道以外的一般结构的损坏。

关键词: 隧道检测, 超高分辨率图像, 深度学习, 病害检测, 图像预处理

Abstract: The data collected by existing tunnel detection techniques usually obtains ultra-high resolution images, and the actual area of the disease in the tunnel is small, which makes the loss of disease information occur after the image has been simply pre-processed (e.g., scaled), and the deep learning model trained under limited computational resources may have a reduced detection rate of the object, unstable training, and other phenomena. To address the above problems, this paper proposes a framework for disease detection based on deep learning and ultra-high resolution images of tunnels, which is applicable to any deep learning model by pre-processing the ultra-high resolution image, segmenting the original image into smaller patch images, and resizing the ultra-high resolution image to a suitable size to improve the performance of the detection model. The experimental results show that the performance of the model under the proposed framework improve by about 77.19% compared with conventional detection process. And the proposed framework is applicable to general ultra-high resolution images, which can effectively identify the damages of general structures other than tunnels.

Key words: tunnel inspection, ultra-high resolution images, deep learning, disease detection, image pre-processing

中图分类号:

P237

马海志. 基于深度学习的隧道超高分辨率图像病害检测框架[J]. 测绘通报, 2025, 0(3): 105-110.

MA Haizhi. Deep learning-based disease detection framework for ultra-high resolution images of tunnels[J]. Bulletin of Surveying and Mapping, 2025, 0(3): 105-110.

参考文献

[1] ZHOU Z,ZHANG J,GONG C.Automatic detection method of tunnel lining multi-defects via an enhanced you only look once network[J].Computer-Aided Civil and Infrastructure Engineering,2022,37(6):762-780.
[2] ZHANG N,ZHU X,REN Y.Analysis and study on crack characteristics of highway tunnel lining[J].Civil Engineering Journal,2019,5(5):1119-1123.
[3] 徐鹏宇,唐超,王丽.轨道交通盾构隧道病害空间分布特征和自相关性研究[J].测绘通报,2021(8):93-96.
[4] 黑焕学.城市轨道交通运营隧道病害辨识与结构健康状态评价[D].北京:北京交通大学,2021.
[5] 李梓豪,唐超,王柄强,等.多源监测数据在隧道结构服役状态评价中的研究与应用[J].测绘通报,2020(9):18-22.
[6] 樊廷立,唐超,王柄强.移动三维激光扫描技术在盾构隧道收敛监测中的应用[J].测绘通报,2020(9):50-53.
[7] 吴晓军,白韶红,啜丙强,等.基于CMOS线阵相机地铁隧道裂缝快速检测系统[J].路基工程,2015(3):185-190.
[8] 刘轩然.基于面阵相机的隧道裂缝图像采集与检测技术[D].北京:北京交通大学,2019.
[9] LIAO J,YUE Y,ZHANG D,et al.Automatic tunnel crack inspection using an efficient mobile imaging module and a lightweight CNN[J].IEEE Transaction on Intelligent Transportation Systems,2022,23(9):15190-15203.
[10] ZHAO S,ZHANG D,XUE Y,et al.A deep learning-based approach for refined crack evaluation from shield tunnel lining images[J].Automation in Construction,2021,132:103934.
[11] HUANG H,ZHAO S,ZHANG D,et al.Deep learning-based instance segmentation of cracks from shield tunnel lining images[J].Structure Infrastructure Engineering,2022,18(2):183-196.
[12] XUE Y,JIA F,CAI X,et al.An optimization strategy to improve the deep learning-based recognition model of leakage in shield tunnels[J].Computer-aided Civil and Infrastructure Engineering,2021,37(3):386-402.
[13] LIU Ziming,GAO Guangyu,SUN Lin,et al.HRDNet:high-resolution detection network for small objects[EB/OL].[2024-06-15].https://arxiv.org/abs/2006.07607v1.
[14] RŮŽI AČU1 KA V,FRANCHETTI F.Fast and accurate object detection in high resolution 4K and 8K video using GPUs[EB/OL].[2024-06-15].https://arxiv.org/abs/1810.10551v1.
[15] ZHANG Y,XU T,WEI Z.Pre-locate net for object detection in high-resolution images[J].China Journal of Aeronautics,2022,35(10):313-325.
[16] AHLSWEDE S,ASAM S,RÖDER A.Hedgerow object detection in very high-resolution satellite images using convolutional neural networks[J].Journal of Applied Remote Sensing,2021,15(1):1-28.
[17] REN Shaoqing,HE Kaiming,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[EB/OL].[2024-06-15].https://arxiv.org/abs/1506.01497v3.
[18] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition,Las Vegas:[s.n.],2016.
[19] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL].[2024-06-15].https://arxiv.org/abs/1409.1556v6.
[20] HOWARD A G,ZHU Menglong,CHEN Bo,et al.MobileNets:efficient convolutional neural networks for mobile vision applications[EB/OL].[2024-06-15].https://arxiv.org/abs/1704.04861v1.
[21] CARUANA R,LAWRENCE S,GILES L.Overfitting in neural nets:Backpropagation,conjugate gradient,and early stopping[C]//Proceedings of the 14th International Conference on Neural Information Processing Systems.Cambridge:MIT Press,2001.