Lightweight Detection of Tunnel Water Leakage Based on Improved YOLOv8 Model

TIAN Chenghang; ZHAO Limeng; LI Yonggang; ZHANG Fangjian; ZHANG Wengang; SUN Weixin; DING Xuanming

doi:10.13409/j.cnki.jdpme.20250430038

您当前的位置：

首页 >

文章列表页 >

Lightweight Detection of Tunnel Water Leakage Based on Improved YOLOv8 Model

更新时间：2026-01-07

- Lightweight Detection of Tunnel Water Leakage Based on Improved YOLOv8 Model
- Journal of Disaster Prevention and Mitigation Engineering Vol. 45, Issue 6, Pages: 1421-1433(2025)
- 作者机构：
  
  1.重庆大学土木工程学院，重庆 400045
  2.山区土木工程安全与韧性全国重点实验室，重庆 400045
  3.广州地铁建设管理有限公司，广东广州 510010
  4.中铁十一局集团有限公司，湖北武汉 430061
  5.重庆大学航空航天学院，重庆 400045
  6.湖南工程学院土木工程智能防灾减灾与生态修复湖南省重点实验室，湖南湘潭， 411104
- 作者简介：
- 基金信息：
- DOI：10.13409/j.cnki.jdpme.20250430038
  CLC： U231.94;U457
- Received：27 March 2025，
  
  Revised：2025-06-09，
  
  Published：28 December 2025
- 稿件说明：
移动端阅览
田城航,赵力萌,李永刚等.基于改进YOLOv8的隧道渗漏水轻量化检测[J].防灾减灾工程学报,2025,45(06):1421-1433.

TIAN Chenghang,ZHAO Limeng,LI Yonggang,et al.Lightweight Detection of Tunnel Water Leakage Based on Improved YOLOv8 Model[J].Journal of Disaster Prevention and Mitigation Engineering,2025,45(06):1421-1433.
田城航,赵力萌,李永刚等.基于改进YOLOv8的隧道渗漏水轻量化检测[J].防灾减灾工程学报,2025,45(06):1421-1433. DOI： 10.13409/j.cnki.jdpme.20250430038.

TIAN Chenghang,ZHAO Limeng,LI Yonggang,et al.Lightweight Detection of Tunnel Water Leakage Based on Improved YOLOv8 Model[J].Journal of Disaster Prevention and Mitigation Engineering,2025,45(06):1421-1433. DOI： 10.13409/j.cnki.jdpme.20250430038.

摘要

针对隧道渗漏水检测中传统方法效率低、现有深度学习模型参数量大且实时性不足的问题，提出一种基于改进YOLOv8n‑seg的轻量化实例分割模型。通过引入Coordinate Attention（CA）注意力机制增强目标区域特征权重，采用MobileNetV4替换主干网络以降低计算复杂度，并结合EfficientHead分割头优化特征解码效率，显著提升了模型在复杂背景下的检测精度与推理速度。实验基于三维激光扫描技术构建的隧道渗漏水数据集（包含3140张增强图像），通过消融实验验证了各模块的有效性：CA机制使平均精度（AP）提升0.82%，MobileNetV4降低参数量43.2%的同时提升AP至81.21%，EfficientHead分割头进一步优化分割细节。联合改进后，模型AP达83.21%，F1值提升至78.53%，参数量仅1.96 M，推理速度达355.2 FPS，较原YOLOv8n‑seg提升6.6%。对比实验表明，改进模型在轻量化指标（参数量、GFLOPs）显著优于Mask R‑CNN等主流模型，且精度接近两阶段方法，满足隧道渗漏水实时检测需求。研究为隧道结构健康监测提供了高效、可靠的轻量化解决方案，具有工程应用价值。

Abstract

To address the challenges of low efficiency in traditional methods for tunnel water leakage detection and the large number of parameters and insufficient real-time performance of existing deep learning models

this study proposed a lightweight instance segmentation model based on an improved YOLOv8n-seg. The coordinate attention (CA) mechanism was introduced to enhance feature representation in target regions. The backbone network was replaced with MobileNetV4 to reduce computational complexity

and the EfficientHead segmentation head was incorporated to improve the efficiency of feature decoding. These improvements collectively enhanced both detection accuracy and inference speed in complex environments. The experiments were conducted on a tunnel water leakage dataset constructed using 3D laser scanning (including 3 140 enhanced images). Ablation experiments were employed to validate the effectiveness of each module. The CA mechanism increased the average precision (AP) by 0.82%

MobileNetV4 increased the AP to 81.21% while reducing the number of parameters by 43.2%

and the EfficientHead further optimized segmentation details. After joint improvements

the model achieved an AP of 83.21%

an F1-score of 78.53%

a number of parameters of 1.96M

and an inference speed of 355.2 FPS

representing a 6.6% increase over the original YOLOv8n-seg. Comparative experiments demonstrated that the proposed model significantly outperformed mainstream models such as Mask R-CNN in lightweight indicators (number of parameters and GFLOPs)

while achieving accuracy comparable to that of two-stage methods

thereby meeting the real-time detection requirement for tunnel water leakage. This study provides an efficient and reliable lightweight solution for structural health monitoring in tunnels

offering practical value for engineering applications.

关键词

Keywords

references

谢森林，胡安峰，肖志荣，等 . 渗漏病害加剧影响下隧道周围土体流变固结分析［J］. 岩石力学与工程学报， 2024 ， 43 （ 10 ）： 2570 ‑ 2580 .

Xie S L ， Hu A F ， Xiao Z R ， et al . Rheological consolidation analysis of soil around tunnels under exacerbated leakage conditions ［J］. Chinese Journal of Rock Mechanics and Engineering ， 2024 ， 43 （ 10 ）： 2570 - 2580 . （in Chinese）

Sun W X ， Han F C ， Zhang Y M ， et al . Experimental assessment of structural responses of tunnels under the groundwater level fluctuation ［J］. Tunnelling and Underground Space Technology ， 2023 ， 137 ： 105138 .

许力之，王耀东，朱力强，等 . 隧道表面图像多目标智能识别算法研究［J］. 铁道学报， 2022 ， 44 （ 9 ）： 154 - 162 .

Xu L Z ， Wang Y D ， Zhu L Q ， et al . Research on algorithm of intelligent recognition of multiple objects of tunnel surface images ［J］. Journal of the China Railway Society ， 2022 ， 44 （ 9 ）： 154 - 162 . （in Chinese）

周鸣亮，汪长松，黄宏伟，等 . 融合机器视觉与性能分析的运营盾构隧道结构安全状态评价［J］. 应用基础与工程科学学报， 2023 ， 31 （ 6 ）： 1461 - 1476 .

Zhou M L ， Wang C S ， Huang H W ， et al . Safety state evaluation of operational shield tunnel structures by integrating computer vision and performance analysis ［J］. Journal of Basic Science and Engineering ， 2023 ， 31 （ 6 ）： 1461 - 1476 . （in Chinese）

Wang S ， Wang L Q ， Zhang W G ， et al . Fracture mode of water-immersed sandstone based on micro CT and statistical damage model under triaxial compression ［J］. Engineering Fracture Mechanics ， 2025 ， 315 ： 110781 .

Wen S H ， Park M ， Tran D Q ， et al . Automated construction safety reporting system integrating deep learning-based real-time advanced detection and visual question answering ［J］. Advances in Engineering Software ， 2024 ， 198 ： 103779 .

Zhou Z P ， Zhuo W ， Cui J Q ， et al . Developing a deep reinforcement learning model for safety risk prediction at subway construction sites ［J］. Reliability Engineering & System Safety ， 2025 ， 257 ： 110885 .

Ding Z K ， Luo L W ， Wang X R ， et al . An artificial intelligence-based method for crack detection in engineering facilities around subways ［J］. Applied Sciences ， 2023 ， 13 （ 19 ）： 11002 .

Zhu A F ， Chen S H ， Lu F F ， et al . Recognition method of tunnel lining defects based on deep learning ［J］. Wireless Communications and Mobile Computing ， 2021 ， 2021 ： 9070182 .

Bani Mustafa A ， Abdel Halim R ， Bulkrock O ， et al . Deep learning for assessing severity of cracks in concrete structures ［J］. International Journal of Computers Communications & Control ， 2023 ， 18 （ 1 ）： 17 - 17 .

Zhou Z ， Li S S ， Yan L B ， et al . Intelligent recognition of tunnel lining defects based on deep learning： Methods， challenges and prospects ［J］. Engineering Failure Analysis ， 2025 ， 170 ： 109332 .

耿鹏 . 基于深度学习的隧道衬砌病害图像检测技术［D］. 石家庄：石家庄铁道大学， 2024 .

Geng P . Tunnel lining disease image detection technology based on deep learning ［D］. Shijiazhuang ： Shijiazhuang Tiedao University ， 2024 . （in Chinese）

Huang H W ， Zhao S ， Zhang D M ， et al . Deep learning-based instance segmentation of cracks from shield tunnel lining images ［J］. Structure and Infrastructure Engineering ， 2022 ， 18 （ 2 ）： 183 - 196 .

Xue Y D ， Cai X Y ， Shadabfar M ， et al . Deep learning-based automatic recognition of water leakage area in shield tunnel lining ［J］. Tunnelling and Underground Space Technology ， 2020 ， 104 ： 103524 .

王宝坤，王如路，陈锦剑，等 . 基于深度学习的盾构隧道表观病害自动检测方法［J］. 上海交通大学学报， 2024 ， 58 （ 11 ）： 1716 - 1723 .

Wang B K ， Wang R L ， Chen J J ， et al . Automatic detection method for surface diseases of shield tunnel based on deep learning ［J］. Journal of Shanghai Jiao Tong University ， 2024 ， 58 （ 11 ）： 1716 - 1723 . （in Chinese）

Zhao S ， Zhang D M ， Huang H W . Deep learning–based image instance segmentation for moisture marks of shield tunnel lining ［J］. Tunnelling and Underground Space Technology ， 2020 ， 95 ： 103156 .

Ouyang A H ， Di Murro V ， Cull M ， et al . Automated pixel-level crack monitoring system for large-scale underground infrastructure： A case study at CERN ［J］. Tunnelling and Underground Space Technology ， 2023 ， 140 ： 105310 .

Xiong L J ， Zhang D L ， Zhang Y . Water leakage image recognition of shield tunnel via learning deep feature representation ［J］. Journal of Visual Communication and Image Representation ， 2020 ， 71 ： 102708 .

宋娟，贺龙喜，龙会平 . 基于深度学习的隧道衬砌多病害检测算法［J］. 浙江大学学报（工学版）， 2024 ， 58 （ 6 ）： 1161 - 1173 .

Song J ， He L X ， Long H P . Deep learning-based algorithm for multi defect detection in tunnel lining ［J］. Journal of Zhejiang University （Engineering Science）， 2024 ， 58 （ 6 ）： 1161 - 1173 . （in Chinese）

Duan S Q ， Zhang M H ， Qiu S L ， et al . Tunnel lining crack detection model based on improved YOLOv5 ［J］. Tunnelling and Underground Space Technology ， 2024 ， 147 ： 105713 .

朱家松，郑澳，雷占占，等 . 基于改进Yolov5的地铁隧道附属设施与衬砌表观病害检测方法［J］. 铁道科学与工程学报， 2023 ， 20 （ 3 ）： 1008 - 1019 .

Zhu J S ， Zheng A ， Lei Z Z ， et al . Metro tunnel accessorial facilities and lining diseases detection method based on improved Yolov5 ［J］. Journal of Railway Science and Engineering ， 2023 ， 20 （ 3 ）： 1008 - 1019 . （in Chinese）

Xu X Q ， Li Q ， Li S E ， et al . Crack width recognition of tunnel tube sheet based on YOLOv8 algorithm and 3D imaging ［J］. Buildings ， 2024 ， 14 （ 2 ）： 531 .

Chen Y P ， Dai X Y ， Liu M C ， et al . Dynamic convolution： Attention over convolution kernels ［C］∥ 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . June 13 - 19 ， 2020 . Seattle， WA， USA ： IEEE ， 2020： 11027 - 11036 .

Tian Z ， Shen C H ， Chen H . Conditional convolutions for instance segmentation ［C］∥ Computer Vision‑ECCV 2020 . Cham， Switzerland ： Springer ， 2020 ： 282 - 298 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Visual Monitoring of Building Seismic Response and Validation through Virtual Reality

Building Damage Identification Method based on Mask R⁃CNN

Application of RISP System to M_S6.2 Taiwan Strait Earthquake Sequence in 2018

Spatiotemporal Forecast of Bluff‑body Wakes Using Artificial Intelligence Technologies

Forecasting of Horizontal Deformation in Retaining Piles of Subway Station Deep Foundation Pits Based on the CEEMDAN⁃SSA⁃ELM⁃LSTM Model

Related Author

ZHAO Xuefeng

LI Shengli

LI Kang

LI Jinke

PENG Fumin

LU Zewei

LI Zhitao

WANG Yuxin

Related Institution

School of Civil Engineering, Zhengzhou University

School of Infrastructure Engineering, Dalian University of Technology

College of Resource and Environment， Institute of Disaster Prevention

Hebei Key Laboratory of Seismic Hazard Instrumentation and Monitoring Technology

Langfang Key Laboratory of Precision Active Source

⁰