All Issue

2025 Vol.24, Issue 4 Preview Page

Research Article

A Study on a Computer Vision-Based Low-Cost Predictive Model for Bridge Safety Monitoring

컴퓨터 비전을 활용한 저비용 교량 안전관리 모니터링 예측 모델 연구

Taewon Park1
,
Seunggil Jeong1
,
Song Choi2
,
Seong-Lim Lee3
,
Bongjun Ji4*
박 태원1
,
정 승길1
,
최 송2
,
이 성림3
,
지 봉준4*
1Member, Master’s Student, Graduate School of Data Science, Pusan National University, 2 Busandaehak-ro, 63beon-gil, Geumjeong-gu, Busan 46241, Republic of Korea
2Member, CEO, Seyon Inc., 26 Beobwon-ro 9-gil, Songpa-gu, Seoul 05836, Republic of Korea
3Member, Team Leader, Seoul Facilities Corporation, 540 Cheonggyecheon-ro, Seongdong-gu, Seoul 04704, Republic of Korea
4Member, Assistant Professor, Graduate School of Data Science, Pusan National University, 2 Busandaehak-ro, 63beon-gil, Geumjeong-gu, Busan 46241, Republic of Korea
*Corresponding Author
30 December 2025. pp. 19-30
PDF XML Citation
Abstract

The aging of critical social infrastructure, including bridges, is a growing concern worldwide, necessitating long-term structural health monitoring and safety management. While conventional methods utilizing contact-based sensors or unmanned aerial vehicles (drones) offer high accuracy, their widespread application is hindered by challenges such as high installation and maintenance costs, limitations to localized measurements, and constraints on long-term operation. To overcome these limitations, this study proposes a novel displacement monitoring methodology that leverages widely available CCTV infrastructure. The proposed technique extracts features from CCTV footage based on Digital Image Correlation (DIC) and converts them into time-series data. Subsequently, deep learning models such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) are applied to estimate the micro-displacements of the bridge. The performance of the proposed methodology was validated using video footage acquired from an actual bridge. The results confirmed a very low error, with a Root Mean Square Error (RMSE) of 0.1116mm, when compared to the actual displacement data measured by contact-based displacement sensors. This research holds significant academic and practical value as it complements the technical and economic shortcomings of existing monitoring methods and presents a new direction for proactively utilizing CCTV infrastructure, an already established societal asset, for bridge safety management.

Keywords
Structural health monitoring
Deep learning
computer vision
Displacement measurement
Bridge safety management
Digital image correlation

교량을 비롯한 핵심 사회기반시설의 노후화는 전 세계적으로 심화되고 있으며, 이에 따른 구조 건전성의 장기적 모니터링 및 안전 관리의 필요성이 증대되고 있다. 기존의 접촉식 센서 기반 계측이나 무인항공기(드론)를 활용하는 방식은 높은 정확도를 제공하지만, 설치 및 유지관리 비용, 국소 계측의 한계, 그리고 장기간 운용의 제약으로 인해 광범위한 적용에 어려움이 존재한다. 본 연구에서는 이러한 한계를 극복하기 위한 대안으로, 광범위하게 보급된 CCTV 인프라를 활용하는 새로운 변위 모니터링 방법론을 제안한다. 제안된 기법은 CCTV 영상에서 디지털 이미지 상관법(Digital Image Correlation) 기반의 특징(Feature)을 추출하고, 이를 시계열 데이터로 변환한 후, Long Short-Term Memory(LSTM) 및 Gated Recurrent Unit(GRU)과 같은 딥러닝 모델을 적용하여 교량의 미소 변위를 추정한다. 실제 교량에서 취득한 영상을 대상으로 제안된 방법론의 성능을 검증한 결과, 접촉식 변위계로 측정한 실제 변위 데이터와 RMSE 기준 0.1116mm 의 매우 적은 오차를 보이는것을 확인하였다. 본 연구는 기존 모니터링 방식의 기술적, 경제적 단점을 보완하고, 이미 구축된 사회적 자산인 CCTV 인프라를 교량 안전 관리에 적극적으로 활용할 수 있는 새로운 방향을 제시한다는 점에서 학술적, 실용적 의의를 가진다.

References
1

Barros, F., Sousa, P., Lobo, P., Tavares, P. J. and Moreira, P. M. G. P. (2022), “Displacement monitoring of a pedestrian bridge using 3D digital image correlation”, Procedia Structural Integrity, Vol.37, pp.880-887.

10.1016/j.prostr.2022.02.022
2

Biondini, F. and Frangopol, D. M. (2018), “Life-cycle performance of deteriorating structural systems under uncertainty: Review”, Structure and Infrastructure Engineering, Vol.14, No.7, pp.1023-1045.

3

Brownjohn, J. M. W. (2007), “Structural health monitoring of civil infrastructure”, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol.365, No.1851, pp.589-622.

10.1098/rsta.2006.1925
4

Bruck, H. A., McNeill, S. R., Sutton, M. A. and Peters, W. H. (1989), “Digital image correlation using Newton-Raphson method of partial differential correction”, Experimental Mechanics, Vol.29, No.3, pp.261-267.

10.1007/BF02321405
5

Choi, J., Kim, H. and Park, J. (2021), “Vision-based structural health monitoring using surveillance cameras: A review”, Sensors, Vol.21, No.19, 6650.

6

Ellenberg, A., Branco, L., Krick, A., Bartoli, I. and Kontsos, A. (2015), “Use of unmanned aerial vehicle for quantitative infrastructure evaluation”, Journal of Infrastructure Systems, Vol.21, No.3, 04014054.

10.1061/(ASCE)IS.1943-555X.0000246
7

Feng, D. and Feng, M. Q. (2018), “Computer vision for SHM of civil infrastructure: From dynamic response measurement to damage detection - A review”, Engineering Structures, Vol.156, pp.105-117.

10.1016/j.engstruct.2017.11.018
8

Feroz, S. and Dabous, S. A. (2021), “UAV-based remote sensing applications for bridge condition assessment”, Remote Sensing, Vol.13, No.9, 1809.

10.3390/rs13091809
9

Frangopol, D. M. and Liu, M. (2007), “Life-cycle cost and performance of civil infrastructure: Trends and challenges”, Structure and Infrastructure Engineering, Vol.3, No.1, pp.29-41.

10.1080/15732470500253164
10

Fu, C. C., Zhao, G., Ye, Y. and Zhang, F. (2015), Serviceability-Related Issues for Bridge Live Load Deflection and Construction Closure Pours, Maryland State Highway Administration, Final Report No.MD-15-SHA-UM-3-12 (SP309B4M), p.77.

11

Hild, F. and Roux, S. (2006), “Digital image correlation: from displacement measurement to identification of elastic properties - a review”, Strain, Vol.42, No.2, pp.69-80.

10.1111/j.1475-1305.2006.00258.x
12

Hoskere, V., Park, J. W., Yoon, H. and Spencer, B. F. (2019), “Vision-based modal survey of civil infrastructure using unmanned aerial vehicles”, Journal of Structural Engineering, Vol.145, No.3, 04019006.

10.1061/(ASCE)ST.1943-541X.0002321
13

Huang, J., Shao, X., Yang, F., Zhu, J. and He, X. (2022), “Measurement method and recent progress of vision-based deflection measurement of bridges: a technical review”, Optical Engineering, Vol.61, No.7, 070901.

10.1117/1.OE.61.7.070901
14

Ji, B. (2021), “Machine Learning-based Concrete Crack Detection Framework for Facility Maintenance,” Journal of the Korean Geo-Environmental Society, Vol.22, No.10, pp.5-12.

15

Lee, J. J. and Shinozuka, M. (2006), “A vision-based system for remote sensing of bridge displacement”, NDT & E International, Vol.39, No.5, pp.425-431.

10.1016/j.ndteint.2005.12.003
16

Lee, S., Kim, Y., Kim, Y., Park, J. and Ji, B. (2025), “Advanced Rock Type Classification Using Deep Learning: A Data-Driven Approach to Tunnel Stability Monitoring and Maintenance,” Journal of the Korean Geosynthetics Society, Vol.24, No.1, pp.89-100.

17

Luo, K., Kong, X., Zhang, J., Hu, J., Li, J. and Tang, H. (2023), “Computer vision-based bridge inspection and monitoring: A review”, Sensors, Vol.23, No.18, p.7863.

10.3390/s2318786337765920PMC10534654
18

Menghini, A., Lanzano, G., Ditommaso, R., Monaco, M. and Dolce, M. (2024), “Estimating bridge stress histories at remote locations from accelerometers, compared to strain gauges”, Engineering Structures, Vol.322, 117429.

10.1016/j.engstruct.2024.118720
19

Ministry of Land, Infrastructure and Transport (MOLIT), (2023), Investigation Report on the Seongnam Jeongja Bridge Collapse, Ministry of Land, Infrastructure and Transport, Sejong.

20

Mousa, M. A., Yussof, M. M., Hussein, T. S., Assi, L. N. and Ghahari, S. (2021), “Application of digital image correlation in structural health monitoring of bridge infrastructures: A review”, Infrastructure, Vol.6, No.12, pp.176-194.

10.3390/infrastructures6120176
21

Panigati, T., Zini, M., Striccoli, D., Giordano, P. F., Tonelli, D., Limongelli, M. P. and Zonta, D. (2025), “Drone-based bridge inspections: Current practices and future directions”, Automation in Construction, Vol.173, 106101.

10.1016/j.autcon.2025.106101
22

Ri, S., Wang, Q., Tsuda, H., Shirasaki, H. and Kuribayashi, K. (2023), “Deflection Measurement of Bridge Using Images Captured Under the Bridge by Sampling Moiré Method”, Experimental Techniques, Vol.47, pp.1085-1095.

10.1007/s40799-022-00616-y
23

Rizzo, P., et al. (2021), “Challenges in bridge health monitoring: A review”, Sensors, Vol.21, No.14, 4671.

10.3390/s2113433634202875PMC8271940
24

Sutton, M. A. (2008), Digital Image Correlation for Shape and Deformation Measurements, In: Sharpe, W. N. (ed.), Springer Handbook of Experimental Solid Mechanics. Springer, Boston, pp.565-600.

10.1007/978-0-387-30877-7_20
25

Yeum, C. M. and Dyke, S. J. (2015), “Vision-based automated crack detection for bridge inspection”, Computer-Aided Civil and Infrastructure Engineering, Vol.30, No.10, pp.759-770.

10.1111/mice.12141
26

Yoneyama, S. and Ueda, H. (2012), “Bridge deflection measurement using digital image correlation with camera movement correction”, Materials Transactions, Vol.53, No.2, pp. 285-290.

10.2320/matertrans.I-M2011843
Information
  • Publisher :Korean Geosythetics Society
  • Publisher(Ko) :한국지반신소재학회
  • Journal Title :Journal of the Korean Geosynthetics Society
  • Journal Title(Ko) :한국지반신소재학회 논문집
  • Volume : 24
  • No :4
  • Pages :19-30
  • Received Date : 2025-09-24
  • Revised Date : 2025-10-23
  • Accepted Date : 2025-10-28
  • DOI :https://doi.org/10.12814/jkgss.2025.24.4.019
Journal Informaiton Journal of the Korean Geosynthetics Society Journal of the Korean Geosynthetics Society
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close