DOI QR코드

DOI QR Code

매장 문화재 공간 분포 결정을 위한 지하투과레이더 영상 분석 자동화 기법 탐색

Automated Analyses of Ground-Penetrating Radar Images to Determine Spatial Distribution of Buried Cultural Heritage

  • 권문희 (충남대학교 우주지질학과) ;
  • 김승섭 (충남대학교 우주지질학과)
  • Kwon, Moonhee (Department of Astronomy, Space Science and Geology, Chungnam National University) ;
  • Kim, Seung-Sep (Department of Astronomy, Space Science and Geology, Chungnam National University)
  • 투고 : 2022.09.21
  • 심사 : 2022.10.28
  • 발행 : 2022.10.28

초록

지구물리탐사기법은 매장 문화재 조사에 필요한 높은 해상도의 지하 구조 영상 생성과 매장 유구의 정확한 위치 결정하는 데 매우 유용하다. 이 연구에서는 경주 신라왕경 중심방의 고해상도 지하투과레이더 영상에서 유구의 규칙적인 배열이나 선형 구조를 자동적으로 구분하기 위하여 영상처리 기법인 영상 특징 추출과 영상분할 기법을 적용하였다. 영상 특징 추출의 대상은 유구의 원형 적심과 선형의 도로 및 담장으로 캐니 윤곽선 검출(Canny edge detection)과 허프 변환(Hough Transform) 알고리듬을 적용하였다. 캐니 윤곽선 검출 알고리듬으로 검출된 윤곽선 이미지에 허프 변환을 적용하여 유구의 위치를 탐사 영상에서 자동 결정하고자 하였으나, 탐사 지역별로 매개변수를 달리해서 적용해야 한다는 제약이 있었다. 영상 분할 기법의 경우 연결요소 분석 알고리듬과 QGIS에서 제공하는 Orfeo Toolbox (OTB)를 이용한 객체기반 영상분석을 적용하였다. 연결 요소 분석 결과에서, 유구에 의한 신호들이 연결된 요소들로 효과적으로 인식되었지만 하나의 유구가 여러 요소로 분할되어 인식되는 경우도 발생함을 확인하였다. 객체기반 영상분석에서는 평균이동(Large-Scale Mean-Shift, LSMS) 영상 분할을 적용하여 각 분할 영역에 대한 화소 정보가 포함된 벡터 레이어를 우선 생성하였고, 유구를 포함하는 영역과 포함하지 않는 영역을 선별하여 훈련 모델을 생성하였다. 이 훈련모델에 기반한 랜덤포레스트 분류기를 이용해 LSMS 영상분할 벡터 레이어에서 유구를 포함하는 영역과 그렇지 않은 영역이 자동 분류 될 수 있음을 확인하였다. 이러한 자동 분류방법을 매장 문화재 지하투과레이더 영상에 적용한다면 유구 발굴 계획에 활용가능한 일관성 있는 결과를 얻을 것으로 기대한다.

Geophysical exploration methods are very useful for generating high-resolution images of underground structures, and such methods can be applied to investigation of buried cultural properties and for determining their exact locations. In this study, image feature extraction and image segmentation methods were applied to automatically distinguish the structures of buried relics from the high-resolution ground-penetrating radar (GPR) images obtained at the center of Silla Kingdom, Gyeongju, South Korea. The major purpose for image feature extraction analyses is identifying the circular features from building remains and the linear features from ancient roads and fences. Feature extraction is implemented by applying the Canny edge detection and Hough transform algorithms. We applied the Hough transforms to the edge image resulted from the Canny algorithm in order to determine the locations the target features. However, the Hough transform requires different parameter settings for each survey sector. As for image segmentation, we applied the connected element labeling algorithm and object-based image analysis using Orfeo Toolbox (OTB) in QGIS. The connected components labeled image shows the signals associated with the target buried relics are effectively connected and labeled. However, we often find multiple labels are assigned to a single structure on the given GPR data. Object-based image analysis was conducted by using a Large-Scale Mean-Shift (LSMS) image segmentation. In this analysis, a vector layer containing pixel values for each segmented polygon was estimated first and then used to build a train-validation dataset by assigning the polygons to one class associated with the buried relics and another class for the background field. With the Random Forest Classifier, we find that the polygons on the LSMS image segmentation layer can be successfully classified into the polygons of the buried relics and those of the background. Thus, we propose that these automatic classification methods applied to the GPR images of buried cultural heritage in this study can be useful to obtain consistent analyses results for planning excavation processes.

키워드

과제정보

이 논문에 대하여 세심한 수정과 의견을 제공해 주신 두 분의 심사위원님들께 감사드립니다. 이 연구는 충남대학교 학술연구비에 의해 지원되었습니다.

참고문헌

  1. Canny, J. (1986) A Computational Approach To Edge Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, v.8(6), p.679-698. doi: 10.1109/TPAMI.1986.4767851
  2. Cultural Heritage Administration-Department of Restoration and Maintenance of Core Heritage Sites of the Silla Kingdom's Capital (2021) The Capital of Silla Reawakens in 2021, Design Gongbang Press, 66p. (in Korean).
  3. Duda, R., Hart, P. (1973) Pattern Classification and Scene Analysis. John Wiley and Sons, p.271-2.
  4. Grizonnet et al. (2017) Orfeo ToolBox: open source processing of remote sensing images. Open Geospatial Data, Software and Standards, v.2(15). DOI 10.1186/s40965-017-0031-6
  5. Gyeongju National Research Institute of Cultural Heritage (2002) Silla Wanggyeong Excavation Report-Hwangnyongsaji East Side S1E1 District, Papyrus Press, jeonju (in Korean).
  6. Gyeongju National Research Institute of Cultural Heritage (2003) A Report on the Excavation of 556 and 566 Inwang-dong, Gyeongju, Seojaemunhwasa, Daegu, p.14-20. (in Korean).
  7. Gyeongju National Research Institute of Cultural Heritage (2010) Current Status and Tasks of Wolseong Research in Gyeongju, Icom, Daegu, p.89-114. (in Korean).
  8. Gyeongju National Research Institute of Cultural Heritage (2016) The Streets of Silla's Capital, Design Gongbang Press, Seoul, p.14-392. (in Korean).
  9. Gyeongju National Research Institute of Cultural Heritage (2021) Gyeongju Wolseong Prelimiary Excavation Survey Report, Design gongbang press, Seoul, 49p. (in Korean).
  10. Michel, J., D. Youssefi and M. Grizonnet, (2015) Stable Mean-Shift Algorithm and Its Application to the Segmentation of Arbitrarily Large Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, v.53(2), p.952-964, doi: 10.1109/TGRS.2014.2330857.
  11. Ju, B.D. (2020) Understanding the Silla Wanggyeong, Julusung press, Seoul (in Korean).
  12. Kim, D.G. (2018) OpenCV Programming with python, Kame Press, Seoul (in Korean).
  13. Kim, E.Y. (2022) The analysis for attributes of OUV of the capital of Shilla Kingdom. Korean Journal of Cultural Heritage Studies, v.55(1), p.151-174. (in Korean with English abstract). doi: 10.22755/KJCHS.2022.55.1.151
  14. Kim, H.O. and Yeom, J.M. (2012) A Study on Object-Based Image Analysis Methods for Land Cover Classification in Agricultural Areas. Journal of the Korean Association of Geographic Information Studies, v.15(4), p.26-41. (in Korean with English abstract). http://dx.doi.org/10.11108/kagis.2012.15.4.026
  15. Kim, J.S. and Kim, D.Y. (2022) Target Detection Method using Lightweight Mean shift Segmentation and Shape Features, Proceedings of the Korean Society of Computer Information Conference, Daejeon, v.30(1), p.41-44. (in Korean).
  16. Lawrence, B.C. (2013) Ground-Penetrating Radar for ArchaeologyThird edition, AltaMira Press, Lanham, 14p.
  17. Lee, J.J. (2021) Paleogeomorphic Analysis of Gyeongju, Symposium on the task of the Paleogemorphic Research of Gyeongju, Gyeongju National Research Institute of Cultural Heritage, Gyeongju, p.3-20. (in Korean).
  18. Lee, S.J. (2019) The Development Process and the Archaeological Boundary of the Silla Kingdom, Symposium on Space and Function of Wolseong and The Capital of Silla Kingdom, Gyeongju National Research Institute of Cultural Heritage.Yeongnam Archaeological Society, Gyeongju, pp.10-23. (in Korean).
  19. Nam, T.H. (2017) Digital Image Processing Basics, B.D. info, Seoul, 326p. (in Korean).
  20. National Research Institute of Cultural Heritage (2006) Excavation and Prospection, Geumgang Press, Daejeon, p.47-52. (in Korean).
  21. National Research Institute of Cultural Heritage and Gyeongju City (2010) Hwangnyongsa Research Series v.6 - A Study on the Restoration of Hwangnyongsa Temple, Korean Disability Economist Daejeon Chungnam Printing Business Group, Deajeon, p.370-482. (in Korean).
  22. National Research Institute of Cultural Heritage (2018) Geophysical Prospection for Archaeology 2018, CN Printech Press, Daejeon, p.68-77.
  23. Oh, H.D. (2021) Large-scale Archaeological Prospection of Silla's Capital, Gyeongju through High-resolution GPR Survey, Doctoral Dissertation, Pusan National University, p.70. (in Korean with English abstract)
  24. Oh, H.D. Kwon, M.H. and Stoyakin, M.A. (2021) Geophysical Prospection on the Ancient Tombs of Katartobe Burial Ground in Kazakhstan, Vestnik NSU. Series: History and Philology. v.20(3), p.36-45. (In Russian with English abstract). https://doi.org/10.25205/1818-7919-2021-20-3-36-45
  25. Park, S.H. and Kim, Y.G. (2017) A Study of Detecting Curved Lane by Hough Transform for Autonomous Driving, The Korean Institute of Information Scientists and Engineers. v.2017(12), p.2104-2106. (in Korean).
  26. Yu, B.H., Park, H.C. and Lee, S.M. (2019) Improvement of Random-Forest OBIA Algorithm for Tree Anomaly Detection in UAV Imagery: Focused on the Birobong-Peak Area of Sobaeksan National Park, Proceedings of Korean Society of Environment & Ecology. Conference, v.29(1), 54p.
  27. Yu, H.E., Jung I.S., Lim, B.S. and Nam, M.J. (2021) Introduction to Useful Attributes for the Interpretation of GPR Data and an Analysis on Past Cases. Geophysics and Geophysical Exploration, v.24(3), p.113-130. (in Korean with English abstract). https://doi.org/10.7582/GGE.2021.24.3.113