Home Journals Articles Updates About
CN
image
收藏切换
Research on Tunnel Core Soil Monitoring Technology Using YOLO-Based Visual Recognition
收藏切换
Ruijun LIAN1, 2, 3, Hanqing LI1, 2, 3, Peiyin LYU3, 4, 5, Songling XING6
Urban Rapid Rail Transit | 2026, 39(2) : 73 - 80
Less
收藏切换
Urban Rapid Rail Transit | 2026, 39(2): 73-80
• Civil Engineering Technology •
Research on Tunnel Core Soil Monitoring Technology Using YOLO-Based Visual Recognition
Full
Ruijun LIAN1, 2, 3, Hanqing LI1, 2, 3, Peiyin LYU3, 4, 5, Songling XING6
Affiliations
  • 1.Beijing MTR Construction Administration Co., Ltd., Beijing 100068
  • 2.Beijing key Laboratory of Fully Automatic Operation and Safety Monitoring For Urban Rail Transit, Beijing 100068
  • 3.Laboratory for Safety Testing Technology of Urban Rail Transit Equipment throughout the Whole Life Cycle, Beijing 100068
  • 4.Beijing Metro Consultancy Corporation Limited, Beijing 100068
  • 5.National Engineering Laboratory for Urban Rail Transit System Safety Assurance Technology, Beijing 100068
  • 6.Beijing Infrastructure Investment Company Limited, Beijing 100101
doi: 10.3969/j.issn.1672-6073.2026.02.009
Outline
收藏切换

In drill-and-blast tunnel construction, the geometric configuration and retained dimensions of the core soil directly influence tunnel settlement magnitude and surrounding rock stability. Traditional manual monitoring methods are inherently subjective, inefficient, and fail to meet real-time monitoring requirements. This paper proposes an automated core soil monitoring method based on an improved YOLO framework. By defining core soil feature points, a standardized annotation system is established. A lightweight detection model incorporating the Convolutional Block Attention Module (CBAM) is designed, effectively suppressing false detections caused by uneven illumination, dust interference, and blurred soil boundaries. Integrated with perspective geometry vanishing point prediction techniques, the VPTR model is employed for vanishing point detection and geometric constraints. This approach corrects perspective distortion errors in core soil cross-section shape calculation, incorporates core soil dimensions and proportions into potential risk classification criteria. For engineering deployment, knowledge distillation and dynamic precision-switching techniques are adopted to enable lightweight operation on edge computing devices, supporting the real-time decision-making demands of "monitoring while excavating".

drill-and-blast tunneling  /  core soil  /  YOLO framework  /  keypoint detection  /  vanishing point detection
廉瑞军, 李汉青, 吕培印, 邢松龄. 基于YOLO视觉识别的隧道核心土监测技术研究. 都市快轨交通, 2026 , 39 (2) : 73 -80 . DOI: 10.3969/j.issn.1672-6073.2026.02.009
Ruijun LIAN, Hanqing LI, Peiyin LYU, Songling XING. Research on Tunnel Core Soil Monitoring Technology Using YOLO-Based Visual Recognition[J]. Urban Rapid Rail Transit, 2026 , 39 (2) : 73 -80 . DOI: 10.3969/j.issn.1672-6073.2026.02.009
Appendix
Less
Year 2026 volume 39 Issue 2
170
46
Cite this Article
BibTeX
Article Info
doi: 10.3969/j.issn.1672-6073.2026.02.009
  • Receive Date：2025-08-25
  • Online Date：2026-09-20
Article Data
Affiliations
History
  • Received：2025-08-25
  • Revised：2025-11-11
Funding
Affiliations
    1.Beijing MTR Construction Administration Co., Ltd., Beijing 100068
    2.Beijing key Laboratory of Fully Automatic Operation and Safety Monitoring For Urban Rail Transit, Beijing 100068
    3.Laboratory for Safety Testing Technology of Urban Rail Transit Equipment throughout the Whole Life Cycle, Beijing 100068
    4.Beijing Metro Consultancy Corporation Limited, Beijing 100068
    5.National Engineering Laboratory for Urban Rail Transit System Safety Assurance Technology, Beijing 100068
    6.Beijing Infrastructure Investment Company Limited, Beijing 100101
References
Share
https://castjournals.cast.org.cn/joweb/dskgjt/EN/10.3969/j.issn.1672-6073.2026.02.009
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT
Links
Articles
Latest Articles
Most Read
Collections
Updates
Events
News
Multimedia
About
About Us
Contact
No. 86 Xueyuan South Road, Haidian District, Beijing
100081
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn

Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House