面向工程结构的视觉振动测量算法综述及其验证应用

金楠; 谭志森; 俞青; 侯思军; 常好诵; 施钟淇; 孙彦龙; 钟儒勉

doi:10.3724/j.gyjzG25103105

面向工程结构的视觉振动测量算法综述及其验证应用

doi: 10.3724/j.gyjzG25103105

金楠^1,2,
谭志森³,
俞青⁴,
侯思军⁵,
常好诵²,
施钟淇^1,2, ,,
孙彦龙^1,2,
钟儒勉⁶

1. 深圳市城市公共安全技术研究院有限公司, 广东深圳 518023;
2. 城市安全发展科技研究院(深圳), 广东深圳 518023;
3. 澳门大学, 澳门 999078;
4. 安置住房保障中心, 北京 100852;
5. 中铁建融城发展有限公司, 成都 610041;
6. 深圳信息职业技术大学, 广东深圳 518000

基金项目:

国家重点研发计划（2024YFC3808605）；广东省普通高校青年创新人才项目（2024KQNCX174）。

详细信息

作者简介:
金楠，博士，高级工程师，主要从事城市安全、智能监测方向研究，jinnan@szsti.org。

通讯作者:
施钟淇,博士,正高级工程师,主要从事城市安全、工程诊治方向研究,shizq@szsti.org。

计量
- 文章访问数: 8
- HTML全文浏览量: 1
- PDF下载量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2025-10-31
- 网络出版日期: 2026-01-06

Validation and Application of Vision-Based Vibration Measurement Algorithms for Engineering Structures

1. Shenzhen Technology Institute of Urban Public Safety，Shenzhen 518023，China;
2. Safe Urban Development Institute of Science and Technology （Shenzhen），Shenzhen 518023，China;
3. University of Macau，Macau 999078，China;
4. Housing Resettlement Center，Beijing 100852，China;
5. CRCC City Interation Development Co.，Ltd.，Chengdu 610041，China;
6. Shenzhen University of Information Technology，Shenzhen 518000，China

摘要

摘要: 梳理了9种主要的视觉振动测量算法，通过统一的室内试验条件开展了公平、系统的性能对比测试。室内对比试验结果表明，基于标记物的方法展现出更高的测量精度，误差平均值EM低至0.92 mm，标准化均方根误差NRMSE低至4.97%。在无标记物方法中，光流法表现最优，其EM为1.5 mm，NRMSE为7.8%，显著优于其他无标记物非接触式测量方法。基于对比试验结论为视觉技术的工程应用提供参考。最后，在工程应用测试中，使用视觉振动测量算法准确提取出结构振动的频率特征，验证了视觉算法在实际工程场景应用中的有效性和泛化能力。
- 工程结构振动测量 /
- 计算机视觉 /
- 多元算法 /
- 性能对比
Abstract: This study systematically evaluated nine mainstream vision-based vibration measurement algorithms through comprehensive performance comparison tests. The results demonstrated that target-based approaches achieved superior measurement accuracy over targetless methods， with an error mean （EM） and normalized root mean square error （NRMSE） as low as 0.92 mm and 4.97%， respectively. Among targetless methods， the optical flow method performed best， with corresponding values of 1.5 mm and 7.8%， significantly outperforming other non-contact targetless approaches. These comparative findings provide valuable guidance for implementing vision-based technologies in engineering. Field applications further confirmed that the algorithms accurately extract structural vibration frequencies， validating their effectiveness and generalization capability in real-world scenarios.
- vibration measurement of engineering structures /
- computer vision /
- multiple algorithms /
- performance comparison

HTML全文

参考文献(30)

[1]	邢逸帆. 调查 \| 第一高楼变“斜塔”:中国买家的旧金山豪宅噩梦[EB/OL].2018[2025-10-31]. https://www.pingwest.com/a/177386.
[2]	朱惠金，熊琛. 基于多自由度弯剪耦合模型的高层建筑异常振动源定位方法研究[C]// 第34届全国结构工程学术会议论文集（第I册）. 深圳:2025:111-114.
[3]	陈蓓儿. 伴随巨响！上海一居民楼楼体发生震动，居民惊慌失措冲下楼，有人大喊:地震了[EB/OL].2024[2025-10-31]. https://news.qq.com/rain/a/20241116A04Q6F00.
[4]	唐文超. 基于计算机视觉的工程结构位移估计与模态参数识别[D]. 深圳:哈尔滨工业大学，2022.
[5]	BROWNJOHN J M W，XU Y，HESTER D. Vision-based bridge deformation monitoring[J]. Frontiers in Built Environment，2017，3:23.
[6]	BHOWMICK S，NAGARAJAIAH S，LAI Z. Measurement of full-field displacement time history of a vibrating continuous edge from video[J]. Mechanical Systems and Signal Processing，2020，144，106847.
[7]	HAN Y，WU G，FENG D. Structural modal identification using a portable laser-and-camera measurement system[J]. Measurement，2023，214，112768.
[8]	TIAN L，PAN B. Remote bridge deflection measurement using an advanced video deflectometer and actively illuminated LED targets[J]. Sensors，2016，16（9），1344.
[9]	DONG C Z，CELIK O，CATBAS F N. Marker-free monitoring of the grandstand structures and modal identification using computer vision methods[J]. Structural Health Monitoring，2019，18（5/6）:1491-1509.
[10]	WANG J，ZHAO J，LIU Y，et al. Vision‐based displacement and joint rotation tracking of frame structure using feature mix with single consumer‐grade camera[J]. Structural Control and Health Monitoring，2021，28（12），e2832.
[11]	LYDON D，LYDON M，TAYLOR S，et al. Development and field testing of a vision-based displacement system using a low cost wireless action camera[J]. Mechanical Systems and Signal Processing，2019，121:343-358.
[12]	LI J，XIE B，ZHAO X. Measuring the interstory drift of buildings by a smartphone using a feature point matching algorithm[J]. Structural Control and Health Monitoring，2020，27（4），e2492.
[13]	CHEN S，ZHAO S，DAI Z，et al. Visual identity‐based earthquake ground displacement testing method[J]. Shock and Vibration，2019，2019（1），2585423.
[14]	HE L，TAN J，HU Q，et al. Non-contact measurement of the surface displacement of a slope based on a smart binocular vision system[J]. Sensors，2018，18（9），2890.
[15]	MALSYMENKO O P，SAKHARUK O M，IVANYTSKYI Y L，et al. Multilaser spot tracking technology for bridge structure displacement measuring[J]. Structural Control and Health Monitoring，2021，28（3），e2675.
[16]	HU Q，HE S，WANG S，et al. A high-speed target-free vision-based sensor for bus rapid transit viaduct vibration measurements using CMT and ORB algorithms[J]. Sensors，2017，17（6），1305.
[17]	YU S，ZHANG J，HE X. An advanced vision-based deformation measurement method and application on a long-span cable-stayed bridge[J]. Measurement Science and Technology，2020，31（6），065201.
[18]	FENG D，FENG M Q，OZER E，et al. A vision-based sensor for noncontact structural displacement measurement[J]. Sensors，2015，15（7）:16557-16575.
[19]	YOON H，ELANWAR H，CHOI H，et al. Target‐free approach for vision‐based structural system identification using consumer‐grade cameras[J]. Structural Control and Health Monitoring，2016，23（12）:1405-1416.
[20]	YANG W，ZHANG X，MA H，et al. Infrared LEDs-based pose estimation with underground camera model for boom-type roadheader in coal mining[J]. IEEE Access，2019，7:33698-33712.
[21]	XU Y，BROWNJOHN J M W. Vision-based systems for structural deformation measurement:case studies[J]. Proceedings of the Institution of Civil Engineers-Structures and Buildings，2018，171（12）:917-930.
[22]	BAY H，ESS A，TUYTELAARS T，et al. Speeded-up robust features（SURF）[J]. Computer Vision and Image Understanding，2008，110（3）:346-359.
[23]	ALCANTARILLA P F，SOLUTIONS T. Fast explicit diffusion for accelerated features in nonlinear scale spaces[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，2011，34（7）:1281-1298.
[24]	YU S，ZHANG J. Fast bridge deflection monitoring through an improved feature tracing algorithm[J]. Computer‐Aided Civil and Infrastructure Engineering，2020，35（3）:292-302.
[25]	高世一，赵明扬，张雷，等. 基于Zernike正交矩的图像亚像素边缘检测算法改进[J]. 自动化学报，2008（9）:1163-1168.
[26]	GHOSAL S，MEHROTRA R. Detection of composite edges[J]. IEEE Transactions on Image Processing，1994，3（1）:14-25.
[27]	凡世玉，刘磊，程正顺. 基于计算机视觉的海上风机叶片结构振动监测[J/OL]. 海洋工程，2025[2025-11-16]. https://link.cnki.net/urlid/32.1423. P.20250917.0937.002.
[28]	ZHAI G，TAN Z，LIANG Y. A novel method for full‐field scale factor calculation under off‐axis measurements for vision‐based structural multipoint displacement measurement and health monitoring[J]. Structural Control and Health Monitoring，2024，2024（1），8416971.
[29]	ZHAI G，LIANG Y，TAN Z，et al. Development of an iterative Otsu method for vision-based structural displacement measurement under low-light conditions[J]. Measurement，2024，226，114182.
[30]	修晟，张愿，单伽锃. 基于视觉和振动监测数据融合的结构动态位移识别及其试验验证[J]. 工程力学，2023，40（11）:90-98.