한국건설순환자원학회논문집 (Journal of the Korean Recycled Construction Resources Institute)

한국건설순환자원학회 (Korean Recycled Construction Resources Institute)
권호 표지
DOI QR코드

DOI QR Code

적대적 생성 신경망과 딥러닝을 이용한 교량 상판의 균열 감지

Crack Detection on Bridge Deck Using Generative Adversarial Networks and Deep Learning

  • 지봉준 (포항공과대학교 산업경영공학과)
  • Ji, Bongjun (Department of Industrial and Management Engineering, Pohang University of Science and Technology)
  • 투고 : 2021.08.24
  • 심사 : 2021.09.01
  • 발행 : 2021.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

교량의 균열은 교량의 상태를 나타내는 중요한 요소이며 주기적인 모니터링 대상이다. 그러나 전문가가 육안으로 점검하는 것은 비용, 시간, 신뢰성 면에서 문제가 있다. 따라서 최근에는 이러한 문제를 극복하기 위해 자동화 가능한 딥러닝 모델을 적용하기 위한 연구가 시작되었다. 딥러닝 모델은 예측할 상황에 대한 충분한 데이터가 필요하지만 교량 균열 데이터는 상대적으로 얻기가 어렵다. 특히 교량의 설계, 위치, 공법에 따라 교량 균열의 형상이 달라질 수 있어 특정 상황에서 많은 양의 균열 데이터를 수집하기 어려움이 따른다. 본 연구에서는 적대적 생성 신경망(Generative Adversarial Network, GAN)을 통해 불충분한 균열 데이터를 생성하고 학습하는 균열 탐지 모델을 개발했다. 본 연구에서는 GAN을 이용하여 주어진 균열 데이터와 통계적으로 유사한 데이터를 성공적으로 생성했으며, 생성된 이미지를 사용하지 않을 때보다 생성된 이미지를 사용할 때 약 3% 더 높은 정확도로 균열 감지가 가능했다. 이러한 접근 방식은 교량의 균열 검출이 필요하지만 균열 데이터는 충분하지 않거나 하나의 클래스에 대한 데이터가 상대적으로 적을 때 감지 모델의 성능을 효과적으로 향상시킬 것으로 기대된다.

Cracks in bridges are important factors that indicate the condition of bridges and should be monitored periodically. However, a visual inspection conducted by a human expert has problems in cost, time, and reliability. Therefore, in recent years, researches to apply a deep learning model are started to be conducted. Deep learning requires sufficient data on the situations to be predicted, but bridge crack data is relatively difficult to obtain. In particular, it is difficult to collect a large amount of crack data in a specific situation because the shape of bridge cracks may vary depending on the bridge's design, location, and construction method. This study developed a crack detection model that generates and trains insufficient crack data through a Generative Adversarial Network. GAN successfully generated data statistically similar to the given crack data, and accordingly, crack detection was possible with about 3% higher accuracy when using the generated image than when the generated image was not used. This approach is expected to effectively improve the performance of the detection model as it is applied when crack detection on bridges is required, though there is not enough data, also when there is relatively little or much data f or one class.

키워드

참고문헌

  1. Dorafshan, S., Maguire, M. (2017). Autonomous detection of concrete cracks on bridge decks and fatigue cracks on steel members, Digital Imaging, 33-44.
  2. Gao, X., Deng, F., Yue, X. (2020). Data augmentation in fault diagnosis based on the Wasserstein generative adversarial network with gradient penalty, Neurocomputing, 396, 487-494. https://doi.org/10.1016/j.neucom.2018.10.109
  3. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y. (2014). Generative adversarial networks, Proceedings of the International Conference on Neural Information Processing Systems(NIPS 2014), 2672-2680.
  4. Han, C., Rundo, L., Araki, R., Furukawa, Y., Mauri, G., Nakayama, H., Hayashi, H. (2020). Infinite brain MR images: PGGAN-based data augmentation for tumor detection, In Neural Approaches to Dynamics of Signal Exchanges, 291-303.
  5. He, H., Garcia, E.A. (2009). Learning from imbalanced data, IEEE Transactions on Knowledge and Data Engineering, 21(9), 1263-1284. https://doi.org/10.1109/TKDE.2008.239
  6. Lee, B.J., Shin, J.I., Park, C.H. (2008). Development of image processing program to inspect concrete bridges, Proceedings of the Korea Concrete Institute Conference, 189-192 [In Korean].
  7. Lee, B.Y., Kim, Y.Y., Kim, J.K. (2005). Development of image processing for concrete surface cracks by employing enhanced binarization and shape analysis technique, Journal of the Korea Concrete Institute, 17(3), 361-368 [in Korean]. https://doi.org/10.4334/JKCI.2005.17.3.361
  8. Lim, S.K., Loo, Y., Tran, N.T., Cheung, N.M., Roig, G., Elovici, Y. (2018). Doping: Generative data augmentation for unsupervised anomaly detection with gan, IEEE International Conference on Data Mining (ICDM) 1122-1127.
  9. Lorencin, I., Baressi Segota, S., Andelic, N., Mrzljak, V., Cabov, T., Spanjol, J., Car, Z. (2021). On urinary bladder cancer diagnosis: Utilization of deep convolutional generative adversarial networks for data augmentation, Biology, 10(3), 175. https://doi.org/10.3390/biology10030175
  10. Mok, T.C., Chung, A.C. (2018). Learning data augmentation for brain tumor segmentation with coarse-to-fine generative adversarial networks, International MICCAI Brainlesion Workshop, 70-80.
  11. Nishikawa, T., Yoshida, J., Sugiyama, T., Fujino, Y. (2012). Concrete crack detection by multiple sequential image filtering, Computer-Aided Civil and Infrastructure Engineering, 27(1), 29-47. https://doi.org/10.1111/j.1467-8667.2011.00716.x
  12. Ortego, P., Diez-Olivan, A., Del Ser, J., Sierra, B. (2020) Data augmentation for industrial prognosis using generative adversarial networks, International Conference on Intelligent Data Engineering and Automated Learning, 113-122.
  13. Peres, R.S., Azevedo, M., Araujo, S.O., Guedes, M., Miranda, F., Barata, J. (2021). Generative adversarial networks for data augmentation in structural adhesive inspection, Applied Sciences, 11(7), 3086. https://doi.org/10.3390/app11073086
  14. Ramponi, G., Protopapas, P., Brambilla, M., Janssen, R. (2018). T-cgan: conditional generative adversarial network for data augmentation in noisy time series with irregular sampling, arXiv preprint arXiv:1811.08295.
  15. Simonyan, K., Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556.
  16. Yamaguchi, T., Hashimoto, S. (2010). Fast crack detection method for large-size concrete surface images using percolation-based image processing, Machine Vision and Applications, 21(5), 797-809. https://doi.org/10.1007/s00138-009-0189-8
  17. Yang, F., Zhang, L., Yu, S., Prokhorov, D., Mei, X., Ling, H. (2019). Feature pyramid and hierarchical boosting network for pavement crack detection, IEEE Transactions on Intelligent Transportation Systems, 21(4), 1525-1535. https://doi.org/10.1109/tits.2019.2910595
  18. Zhu, Z., German, S., Brilakis, I. (2011). Visual retrieval of concrete crack properties for automated post-earthquake structural safety evaluation, Automation in Construction, 20(7), 874-883. https://doi.org/10.1016/j.autcon.2011.03.004
  19. Zou, Q., Zhang, Z., Li, Q., Qi, X., Wang, Q., Wang, S. (2018). Deepcrack: Learning hierarchical convolutional features for crack detection, IEEE Transactions on Image Processing, 28(3), 1498-1512. https://doi.org/10.1109/tip.2018.2878966