Tunnel and Underground Space (터널과지하공간)

Korean Society for Rock Mechanics and Rock Engineering (한국암반공학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Automatic Classification of Characterized Ground Regions on Slopes by a Deep Learning based Image Segmentation

딥러닝 영상처리를 통한 비탈면의 지반 특성화 영역 자동 분류에 관한 연구

  • Lee, Kyu Beom (University of Science and Technology & Korea Institute of Civil Engineering and Building Technology) ;
  • Shin, Hyu-Soung (Korea Institute of Civil Engineering and Building Technology) ;
  • Kim, Seung Hyeon (Korea Institute of Civil Engineering and Building Technology) ;
  • Ha, Dae Mok (Seoul National University of Science and Technology) ;
  • Choi, Isu (Hanyang University)
  • 이규범 (한국과학기술연합대학원대학교&한국건설기술연구원) ;
  • 신휴성 (한국건설기술연구원) ;
  • 김승현 (한국건설기술연구원) ;
  • 하대목 (서울과학기술대학교) ;
  • 최이수 (한양대학교)
  • Received : 2019.12.09
  • Accepted : 2019.12.23
  • Published : 2019.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Because of the slope failure, not only property damage but also human damage can occur, slope stability analysis should be conducted to predict and reinforce of the slope. This paper, defines the ground areas that can be characterized in terms of slope failure such as Rockmass jointset, Rockmass fault, Soil, Leakage water and Crush zone in sloped images. As a result, it was shown that the deep learning instance segmentation network can be used to recognize and automatically segment the precise shape of the ground region with different characteristics shown in the image. It showed the possibility of supporting the slope mapping work and automatically calculating the ground characteristics information of slopes necessary for decision making such as slope reinforcement.

비탈면의 붕괴로 인해 재산피해뿐만 아니라 인명피해 또한 발생할 수 있으므로 안정성 평가를 통해 비탈면의 붕괴여부 예측 및 보강을 진행해야 한다. 본 논문은 비탈면 영상에서 암반 절리군, 암반 단층, 토양, 비탈면 누수영역 등 비탈면 붕괴와 관련하여 특성화 시킬 수 있는 지반 영역들을 정의하고 이를 딥러닝 기법을 통해 자동으로 분류해 낼 수 있는 방법에 대해 고찰하였다. 이에 따라 딥러닝 객체 영역분할(Instance segmentation) 네트워크를 활용하여 영상에 보여지는 다른 특성을 갖는 지반영역의 정확한 형상을 인식하고 자동 분할 할 수 있음을 보였으며, 향후 비탈면 안정성 평가를 위해 시행되는 비탈면 매핑 작업을 지원하고, 비탈면 보강 대책 등 의사결정에 필요한 비탈면의 지반특성 정보를 자동으로 산출할 수 있는 가능성을 보였다.

Keywords

References

  1. Brooks, J., 2019, COCO Annotator, https://github.com/jsbroks/coco-annotator/
  2. He, K., Gkioxari, G., Dollar, P., and Girshick, R., 2017, Mask r-cnn, In Proceedings of the IEEE international conference on computer vision, pp. 2961-2969.
  3. He, K., Zhang, X., Ren, S., and Sun, J., 2016, Deep residual learning for image recognition, In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778.
  4. Ioffe, S., and Szegedy, C., 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv preprint arXiv:1502.03167.
  5. Kim, J., H., and Kim, J., D., 2001, 암반 비탈면 영상을 이용한 절리의 방향성 해석, 한국암반공학회 학술대회 및 세미나 자료집, pp. 59-68.
  6. Kim, J., T., Lee, C., J., Kim, J., H., Lee, Y., S., Ahn, K., H., Kim, S., D., and Jeong, G., C., 2008, Mapping and Slope Stability Analysis in Weathered Gneiss, Conference of Korean Society of Engineering Geology, pp. 163-170.
  7. Korea Institute of Civil Engineering and Building Technology(KICT), 2016, 옥동-농소 2공구 도로개설공사: 비탈면 정밀조사 및 대책안 제시 검토의견서.
  8. Krizhevsky, A., Sutskever, I., and Hinton, G. E., 2012, Imagenet classification with deep convolutional neural networks, In Advances in neural information processing systems, pp. 1097-1105.
  9. LeCun, Y., Bengio, Y., and Hinton, G., 2015, Deep learning, Nature, Vol. 521, pp. 436-444. https://doi.org/10.1038/nature14539
  10. Lim, C.U., 2017, Mask R-CNN, www.slideshare.net/windmdk/mask-rcnn
  11. Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Bourdev, J., Girshick , R., Dollar, P., and Zitnick, C. L., 2014, Microsoft coco: Common objects in context, In European conference on computer vision, pp. 740-755.
  12. Ministry of Land, Transport and Maritime Affairs(MLTMA), 2011, 도로비탈면 유지관리 실무매뉴얼.
  13. Nair, V., and Hinton, G. E., 2010, Rectified linear units improve restricted boltzmann machines, In Proceedings of the 27th international conference on machine learning (ICML-10), pp. 807-814.
  14. Park, D. G., Kim, T. H., and Park, J. H., 2006, 우리나라 비탈면재해 피해현황과 대책, Geotechnical Engineering, Vol. 22, No. 6, pp. 6-18.
  15. Ren, S., He, K., Girshick, R., and Sun, J., 2015, Faster r-cnn: Towards real-time object detection with region proposal networks, In Advances in neural information processing systems, pp. 91-99.
  16. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R., 2014, Dropout: a simple way to prevent neural networks from overfitting, The journal of machine learning research, Vol. 15, No. 1, pp. 1929-1958.
  17. Voulodimos, A., Doulamis, N., Doulamis, A., and Protopapadakis, E., 2018, Deep learning for computer vision: A brief review, Computational intelligence and neuroscience.
  18. Zhao, H., 2018, New image processing algorithm for geological structure identification of rock slopes based on drone-captured images, PhD Thesis, Colorado School of Mines, Arthur Lakes Library.
  19. Zhu, M., 2004, Recall, precision and average precision, Department of Statistics and Actuarial Science, University of Waterloo.
  20. Zitnick, C. L., and Dollar, P., 2014, Edge boxes: Locating object proposals from edges, In European conference on computer vision, pp. 391-405.