터널과지하공간 (Tunnel and Underground Space)

  • 제29권4호
  • /
  • Pages.230-242
  • /
  • 2019
  • /
  • 1225-1275(pISSN)
  • /
  • 2287-1748(eISSN)
한국암반공학회 (Korean Society for Rock Mechanics and Rock Engineering)
권호 표지
DOI QR코드

DOI QR Code

자동 균열 조사기법의 정확도 평가를 위한 조사선 기반의 지표 제안

Scanline Based Metric for Evaluating the Accuracy of Automatic Fracture Survey Methods

  • 김진언 (서울대학교 에너지시스템공학부) ;
  • 송재준 (서울대학교 에너지시스템공학부)
  • Kim, Jineon (Department of Energy Systems Engineering, Seoul National University) ;
  • Song, Jae-Joon (Department of Energy Systems Engineering, Seoul National University)
  • 투고 : 2019.07.31
  • 심사 : 2019.08.22
  • 발행 : 2019.08.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

신속한 암반 및 암석 균열 조사를 위해서는 자동화된 조사기법이 필요하다. 그러나 자동 조사기법의 균열 지도가 수동으로 조사한 것과 얼마나 일치하는지 표기하는 단일 지표가 없어서 그 정확도를 평가하는데 어려움이 있다. 따라서 본 연구에서는 균열 지도 간의 일치도를 단일 값으로 표현하는 조사선 교차 일치도 (Scanline Intersection Similarity, SIS)라는 지표를 새롭게 제안하였다. 제안된 지표는 두 균열 지도의 균열 빈도를 다수의 조사선 상에서 비교하여 이들 간의 기하학적 일치도를 도출한다. 해당 지표의 적용성을 검토하기 위해 컴퓨터 비전 (Computer Vision) 분야에서 널리 사용하는 일치도 지표인 Intersection Over Union (IoU)과 비교분석하였다. IoU는 균열의 미시적 형태 차이를 과대평가하는 반면에, 제안된 지표의 경우 미시적 형태 차이보다 경사와 같은 거시적 형태 차이를 더 민감하게 반영하였다. 따라서 균열의 거시적 형태가 중요한 암반 공학적 관점에서, 제안된 지표가 IoU 보다 균열 지도의 일치도 지표로써 적합하였다. 더 나아가 제안된 지표를 딥러닝(Deep Learning)을 이용한 균열 조사기법에 적용해본 결과, 해당 기법의 정확도가 조사선 교차 일치도로 0.674 임을 확인하였다.

While various automatic rock fracture survey methods have been researched, the evaluation of the accuracy of these methods raises issues due to the absence of a metric which fully expresses the similarity between automatic and manual fracture maps. Therefore, this paper proposes a geometry similarity metric which is especially designed to determine the overall similarity of fracture maps and to evaluate the accuracy of rock fracture survey methods by a single number. The proposed metric, Scanline Intersection Similarity (SIS), is derived by conducting a large number of scanline surveys upon two fracture maps using Python code. By comparing the frequency of intersections over a large number of scanlines, SIS is able to express the overall similarity between two fracture maps. The proposed metric was compared with Intersection Over Union (IoU) which is a widely used evaluation metric in computer vision. Results showed that IoU is inappropriate for evaluating the geometry similarity of fracture maps because it is overly sensitive to minor geometry differences of thin elongated objects. The proposed metric, on the other hand, reflected macro-geometry differences rather than micro-geometry differences, showing good agreement with human perception. The metric was further applied to evaluate the accuracy of a deep learning-based automatic fracture surveying method which resulted as 0.674 (SIS). However, the proposed metric is currently limited to 2D fracture maps and requires comparison with rock joint parameters such as RQD.

키워드

참고문헌

  1. Barton, N., Lien, R. and Lunde, J., 1974, Engineering classification of rock masses for the design of tunnel support, Rock mechanics, 6(4), 189-236. https://doi.org/10.1007/BF01239496
  2. Byun, H., Yoon, D., Kang, I., Kim, J. and Song, J., 2018, Automated Rock Fracture Detection Using a Convolutional Neural Network, Proceedings of 2018 Fall Joint Conference of KSMER.KSRM.MIRECO, Gangwon-do, South Korea.
  3. Csurka, G., Larlus, D. and Perronnin, F., 2013, What Is a Good Evaluation Measure for Semantic Segmentation?, Procedings of the 24th British Machine Vision Conference 2013, https://doi.org/10.5244/C.27.32.
  4. Deb, D., Hariharan, S., Rao, U.M. and Ryu, C.H., 2008, Automatic Detection and Analysis of Discontinuity Geometry of Rock Mass from Digital Images, Computers and Geosciences, 34(2), 115-26, https://doi.org/10.1016/j.cageo.2007.03.007.
  5. Everingham, M., Gool, L., Williams, C., Winn, J. and Zisserman, A., 2010, The Pascal Visual Object Classes (VOC) Challenge, Int. J. Comput. Vision, 88(2), 303-38, https://doi.org/10.1007/s11263-009-0275-4.
  6. Ferrero, A. M., Forlani, G., Roncella, R. and Voyat, H. I., 2009, Advanced Geostructural Survey Methods Applied to Rock Mass Characterization, Rock Mechanics and Rock Engineering, 42(4), 631-65, https://doi.org/10.1007/s00603-008-0010-4.
  7. Han, J.H. and Song, J.J., 2007, Study on Applicability of Stereophotogrammetry to Rock Joint Survey, Tunnel and Underground Space, 17(2), 139-151.
  8. Han, J.H., Song, J.J. and Jo, Y.D., 2009, Effect of Photographing Light Intensity on Rock Joint Survey in Mine Tunnels Using Stereophotogrammetry, Tunnel and Underground Space, 19(6), 517-25.
  9. Hudson, J. A. and Priest, S. D., 1983, Discontinuity Frequency in Rock Masses, International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts, 20(2), 73-89, https://doi.org/10.1016/0148-9062(83)90329-7.
  10. Hyun, S., Lee, J.S., Jeon, S., Kim, Y., Kim, K.Y. and Yun. T.S., 2019, Pixel-level Crack Detection in X-ray Computed Tomography Image of Granite using Deep Learning, Tunnel and Underground Space, 29(3), 184-196. https://doi.org/10.7474/TUS.2019.29.3.184
  11. Lee, H.C., Kwon, K.M., Moon, C.E. and Jo, Y.H., 2018, Measurement Equipment Development of Stability Evaluation for Joint Slope using Unmaned Aerial Vehicle, Tunnel and Underground Space, 28(3), 193-208. https://doi.org/10.7474/TUS.2018.28.3.193
  12. Lemy, F., and Hadjigeorgiou, J., 2003, Discontinuity Trace Map Construction Using Photographs of Rock Exposures, International Journal of Rock Mechanics and Mining Sciences, 40, 903-17, https://doi.org/10.1016/S1365-1609(03)00069-8.
  13. Li, X., Chen, J. and Zhu, H., 2016, A New Method for Automated Discontinuity Trace Mapping on Rock Mass 3D Surface Model, Computers and Geosciences, 89, 118-31, https://doi.org/10.1016/j.cageo.2015.12.010.
  14. Mohebbi, M., Yarahmadi Bafghi, A. R., Fatehi Marji, M. and Gholamnejad, J., 2016, Rock Mass Structural Data Analysis Using Image Processing Techniques (Case Study: Choghart Iron Ore Mine Northern Slopes), Journal of Mining & Environment, 8(May), 61-74, https://doi.org/10.22044/jme.2016.629.
  15. Powers, D. M. W, 2011, Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness and Correlation, Journal of Machine Learning Technologies, 2(1), 37-63, https://doi.org/10.1.1.214.9232. https://doi.org/10.1.1.214.9232
  16. Shi, R., King, N. N. and Li, S., 2014, Jaccard Index Compensation for Object Segmentation Evaluation, 2014 IEEE International Conference on Image Processing (ICIP), Paris, 4457-61, https://doi.org/10.1109/ICIP.2014.7025904.