KSCE Journal of Civil and Environmental Engineering Research (대한토목학회논문집)

Korean Society of Civil Engeneers (대한토목학회)
권호 표지
DOI QR코드

DOI QR Code

Development of Deep Learning-Based Damage Detection Prototype for Concrete Bridge Condition Evaluation

콘크리트 교량 상태평가를 위한 딥러닝 기반 손상 탐지 프로토타입 개발

  • 남우석 (부산대학교 사회환경시스템공학과, 국토안전관리원 기업성장응답센터) ;
  • 정현준 (국토안전관리원 디지털혁신추진단 빅데이터전략팀) ;
  • 박경한 (국토안전관리원 안전성능연구소 정책연구실) ;
  • 김철민 (국토안전관리원 안전성능연구소 기술개발실) ;
  • 김규선 (국토안전관리원 경영본부 경영관리실)
  • Received : 2021.07.23
  • Accepted : 2021.11.25
  • Published : 2022.02.01
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, research has been actively conducted on the technology of inspection facilities through image-based analysis assessment of human-inaccessible facilities. This research was conducted to study the conditions of deep learning-based imaging data on bridges and to develop an evaluation prototype program for bridges. To develop a deep learning-based bridge damage detection prototype, the Semantic Segmentation model, which enables damage detection and quantification among deep learning models, applied Mask-RCNN and constructed learning data 5,140 (including open-data) and labeling suitable for damage types. As a result of performance modeling verification, precision and reproduction rate analysis of concrete cracks, stripping/slapping, rebar exposure and paint stripping showed that the precision was 95.2 %, and the recall was 93.8 %. A 2nd performance verification was performed on onsite data of crack concrete using damage rate of bridge members.

최근 안전점검자가 접근성 문제로 점검이 어려운 교량 부재의 상태평가를 위해 영상분석 기반의 시설물 점검 기법연구가 활발히 진행 중이다. 본 논문은 교량을 대상으로 딥러닝 기반 영상정보에 대해서 상태평가 연구를 진행하였고 이에 대한 평가 프로그램(프로토타입)을 개발하였다. 딥러닝 기반 교량 손상탐지 프로토타입을 개발하기 위해 딥러닝 모델 중 손상 검출 및 정량화가 가능한 의미론적 분할 모델인 Mask-RCNN를 적용하였고 학습데이터 6,540장(오픈 데이터 포함)과 손상유형에 적합한 레이블링을 구성하였다. 모델링에 대한 성능검증한 결과, 콘크리트 균열, 박리/박락, 철근노출과 도장 박리에 대한 정밀도(precision)는 95.2 %, 재현율(recall)은 93.8 % 나타내었다. 또한, 교량 콘크리트 부재 손상율을 이용하여 콘크리트 균열 실 데이터를 2차 성능검증 하였다.

Keywords

Acknowledgement

이 연구는 국토교통과학기술진흥원(과제번호: 21CTAP-C152144-03)의 지원으로 수행되었습니다.

References

  1. Amhaz, R., Chambon, S., Idier, J. and Baltazart, V. (2016). "Automatic crack detection on 2D pavement images: An algorithm based on minimal path selection." IEEE Transaction on Intelligent Transportation System, Vol. 17, No. 10, pp. 2718-2729. https://doi.org/10.1109/TITS.2015.2477675
  2. Cui, L., Qi, Z., Chen, Z., Meng, F. and Shi, Y. (2015). "Pavement distress detection using random decision forests." International Conference on Data Science, Springer, Cham, pp. 95-102.
  3. Dorafshan, S., Maguire, M. and Qi, X. (2016). Automatic surface crack detection in concrete structures using OTSU thresholding and morphological operations, UTC Report 01-2016, Utah State University, Logan, Utah, USA.
  4. Dorafshan, S., Thomas, J. R. and Maguire, M. (2018a). "Comparison of deep learning convolutional neural networks and edge detectors for image-based crack detection in concrete." Construction and Building Materials, Vol. 186, pp. 1031-1045. https://doi.org/10.1016/j.conbuildmat.2018.08.011
  5. Dorafshan, S., Thomas, R. J., Coopmans, C. and Maguire, M. (2018b). "Deep learning neural networks for sUAS-assisted structural inspections, feasibility and application." 2018 International Conference on Unmanned Aircraft Systems, ICUAS, Dallas, TX.
  6. Hoskere, V., Narazaki, Y., Hoang, T. A. and Spencer Jr, B. F. (2017). Vision-based structural inspection using multiscale deep convolutional neural networks, 3rd Huixian International Forum on Earthquake Engineering for Young Researchers, August 11-12, 2017, University of Illinois, Urbana-Champaign, United States.
  7. Lee, Y. I., Kim, B. H. and Cho, S. J. (2018). "Image-based spalling detection of concrete structures using deep learning." Journal of the Korea Concrete Institute, Vol. 30, No. 1, pp. 91-99. https://doi.org/10.4334/jkci.2018.30.1.091
  8. Li, H., Song, D., Liu, Y. and Li, B. (2017). Automatic pavement crack detection by multi-scale image fusion, TR 2017-11-1, Department of Computer Science and Engineering, Texas A&M University.
  9. Shi, Y., Cui, L., Qi, Z., Meng, F. and Chen, Z. (2016). "Automatic road crack detection using random structured forests." IEEE Transactions on Intelligent Transportation Systems, Vol. 17, No. 12, pp. 3434-3445. https://doi.org/10.1109/TITS.2016.2552248
  10. Yang, L., Li, B., Li, W., Zhaoming, L., Yang, G. and Xiao, J. (2017a). "Deep concrete inspection using unmanned aerial vehicle towards CSSC database." 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS.
  11. Yang, L., Li, B., Li, W., Liu, Z., Yang, G. and Xiao, J. (2017b). "A robotic system towards concrete structure spalling and crack database." 2017 IEEE International Conference on Robotics and\ Biomimetics, ROBIO.
  12. Zhang, L., Yang, F., Zhang, Y. D. and Zhu, Y. J. (2016). "Road crack detection using deep convolutional neural network." 2016 IEEE International Conference on Image Processing, ICIP, DOI: http://doi.org/10.1109/ICIP.2016.7533052.