[1]朱波,侯明坤.视觉监测系统在邻近铁路营业线施工中路基监测的应用研究[J].高速铁路技术,2026,(01):111-117.[doi:10.12098/j.issn.1674-8247.2026.01.016]
　ZHU Bo,HOU Mingkun.Application of Visual Monitoring System in Subgrade Monitoring for Construction adjacent to Operational Railway Lines[J].HIGH SPEED RAILWAY TECHNOLOGY,2026,(01):111-117.[doi:10.12098/j.issn.1674-8247.2026.01.016]
点击复制

视觉监测系统在邻近铁路营业线施工中路基监测的应用研究()

《高速铁路技术》[ISSN:1674-8247/CN:51-1730/U]

卷:
期数:
2026年01期
页码:
111-117
栏目:
研究创新
出版日期:
2026-01-30

文章信息/Info

Title:
Application of Visual Monitoring System in Subgrade Monitoring for Construction adjacent to Operational Railway Lines
文章编号:
1674-8247(2026)01-0111-07
作者:
朱波; 侯明坤
(云南铁路工程项目管理有限责任公司, 昆明 650200)
Author(s):
ZHU Bo;  HOU Mingkun
(Yunnan Railway Engineering Project Management Co., Ltd., Kunming 650200, China)
关键词:
视觉监测;  路基监测;  病害识别;  智能预警;  特征匹配
Keywords:
visual monitoring;  subgrade monitoring;  disease identification;  intelligent early warning;  feature matching
分类号:
U213.1
DOI:
10.12098/j.issn.1674-8247.2026.01.016
文献标志码:
A
摘要:
为解决传统铁路路基监测方法效率低、成本高、实时性差的问题,研究了一种基于机器视觉的智能化监测方案。通过构建包含高帧率相机、自适应云台与边缘计算终端的硬件系统,并融合中值滤波、小波去噪、改进ORB特征匹配与轻量化卷积神经网络等算法,实现了对路基变形与病害的高精度、全天候自动识别与预警。系统在某邻近营业线的棚洞施工项目中进行了试点应用,结果表明,该系统对边坡与路基位移监测的平均精度达0.8 mm,预警响应时间仅需30 min,有效数据获取率超过96.7%。与传统方法相比,该系统显著提升了监测效率与安全性,降低了人工成本,为铁路路基的智能运维提供了可靠的技术支撑。
Abstract:
To solve the problems of low efficiency, high cost, and poor real-time performance of traditional railway subgrade monitoring methods, an intelligent monitoring scheme based on machine vision was studied. By constructing a hardware system comprising high frame rate cameras, adaptive pan-tilt units and edge computing terminals, and integrating median filtering, wavelet denoising, improved ORB feature matching and lightweight convolutional neural network and other algorithms, the high-precision, all-weather automatic identification and early warning of subgrade deformation and disease were realized. The system was piloted in a construction project involving a shed-tunnel structure adjacent to an operational railway line. Results show that the system attains an average accuracy of 0.8 mm in monitoring slope and subgrade displacement, with an early warning response time of only 30 minutes and an effective data acquisition rate exceeding 96.7%. Compared to traditional methods, this system significantly improves monitoring efficiency and safety while reducing labor costs, providing reliable technical support for the intelligent operation and maintenance of railway subgrade.

参考文献/References:

[1] 熊睿, 邓院昌. 疲劳驾驶交通事故的严重程度影响因素分析[J]. 中国安全生产科学技术, 2022, 18(4): 20-26.
XIONG Rui, DENG Yuanchang. Analysis on Factors Affecting Severity of Traffic Accidents Caused by Fatigue Driving[J]. Journal of Safety Science and Technology, 2022, 18(4): 20-26.
[2] 王勇, 郭永贞, 张飞, 等. 基于北斗定位技术的铁路路基形变监测系统[J]. 中国铁路, 2023(6): 123-129.
WANG Yong, GUO Yongzhen, ZHANG Fei, et al. Railway Subgrade Deformation Monitoring System Based on Beidou Positioning Technology[J]. Chinese Railways, 2023(6): 123-129.
[3] 陈国真, 肖周阳. 三维激光扫描在地铁隧道形变监测中的应用[J]. 交通建设与管理, 2023(3): 134-135.
CHEN Guozhen, XIAO Zhouyang. Application of Three-dimensional Laser Scanning in Deformation Monitoring of Subway Tunnel[J]. Transport Construction & Management, 2023(3): 134-135.
[4] “十四五”铁路科技创新规划[J]. 铁道技术监督, 2022, 50(1): 9-15, 20.
Railway Science and Technology Innovation Plan in the 14th Five-Year Plan[J]. Railway Quality Control, 2022, 50(1): 9-15, 20.
[5] YE X W, DONG C Z, LIU T. A Review of Machine Vision-based Structural Health Monitoring: Methodologies and Applications[J]. Journal of Sensors, 2016, 2016: 7103039.
[6] 朱军, 张天奕, 谢亚坤, 等. 顾及小目标特征的视频人流量智能统计方法[J]. 西南交通大学学报, 2022, 57(4): 705-712, 736.
ZHU Jun, ZHANG Tianyi, XIE Yakun, et al. Intelligent Statistic Method for Video Pedestrian Flow Considering Small Object Features[J]. Journal of Southwest Jiaotong University, 2022, 57(4): 705-712, 736.
[7] 高速铁路基础设施运用状态检测管理办法 [J]. 中华人民共和国国务院公报, 2019,(1): 55-58.
Measures for the Management of Condition Detection and Monitoring of High-speed Railway Infrastructure in Use [J]. Gazette of the State Council of the People's Republic of China, 2019,(1): 55-58.
[8] 国家铁路局. 关于印发《铁路营业线施工安全管理办法》:国铁运输监〔2021〕31号 [EB/OL].(2021-09-30)[2024-10-01].https://www.gov.cn/gongbao/content/2021/content_5662018.htm.
National Railway Administration of the People's Republic of China. Notice on the Issuance of the “Safety Management Measures for Railway Operational Line Construction”: Guo Tie Yun Shu Jian〔2021〕No. 31[EB/OL].(2021-09-30)[2024-10-01]. https://www.gov.cn/gongbao/content/2021/content_5662018.htm.
[9] 黄磊, 禹聪. 基于区域化数字图像的边坡监测方法研究[J]. 云南电力技术, 2025, 53(4): 61-65.
HUANG Lei, YU Cong. Research on Regionalised Digital Image Based Slope Monitoring Methods[J]. Yunnan Electric Power, 2025, 53(4): 61-65.
[10] 李瑞琦, 鲍艳, 卢建军, 等. 一种新型隧道图像去噪方法: 基于小波变换及中值滤波的隧道图像去噪方法研究[J]. 现代信息科技, 2020, 4(22): 81-85.
LI Ruiqi, BAO Yan, LU Jianjun, et al. A New Denoising Method for Tunnel Image—Research on Tunnel Image Denoising Method Based on Wavelet Transform and Median Filter[J]. Modern Information Technology, 2020, 4(22): 81-85.
[11] REN Fei, XU Libing, FEI Jiajie, et al. Design of Multi-mode Intelligent System Architecture for Surface Defect Detection of Steel Based on Cloud Technology[J]. Scientific Reports, 2025, 15: 39735.
[12] 李文静, 白静, 彭斌, 等. 图卷积神经网络及其在图像识别领域的应用综述[J]. 计算机工程与应用, 2023, 59(22): 15-35.
LI Wenjing, BAI Jing, PENG Bin, et al. Graph Convolutional Neural Network and Its Application in Image Recognition[J]. Computer Engineering and Applications, 2023, 59(22): 15-35.
[13] FENG Di, HAASE-SCHUTZ C, ROSENBAUM L, et al. Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(3): 1341-1360.

备注/Memo

备注/Memo:
收稿日期:2025-09-21
作者简介:朱波(1978-),男,高级工程师。
更新日期/Last Update: 2026-01-30