DOI QR코드

DOI QR Code

Height Determination Using Vanishing Points of a Single Camera for Monitoring of Construction Site

건설현장 모니터링을 위한 단안 카메라 기반의 소실점을 이용한 높이 결정

  • Choi, In-Ha (Department of Spatial Information Engineering, Namseoul University) ;
  • So, Hyeong-Yoon (Department of Spatial Information Engineering, Namseoul University) ;
  • Kim, Eui-Myoung (Department of Drone.GIS Engineering, Namseoul University)
  • 최인하 (남서울대학교 공간정보공학과) ;
  • 소형윤 (남서울대학교 공간정보공학과) ;
  • 김의명 (남서울대학교 드론공간정보공학과)
  • Received : 2021.09.13
  • Accepted : 2021.11.25
  • Published : 2021.12.10

Abstract

According to the government's announcement of the safety management enhancement policy for small and medium-sized private construction sites, the subject of mandatory CCTV installation has been expanded from large construction sites to small and medium-sized construction sites. However, since the existing CCTV at construction sites has been used for simple control for safety management, so research is needed for monitoring of construction sites. Therefore, in this study, three vanishing points were calculated based on a single image taken with a monocular camera, and then a camera matrix containing interior orientation parameters information was determined. And the accuracy was verified by calculating the height of the target object from the height of the reference object. Through height determination experiments using vanishing points based on a monocular camera, it was possible to determine the height of target objects only with a single image without separately surveying of ground control points. As a result of the accuracy evaluation, the root mean square error was ±0.161m. Therefore, it is determined that the progress of construction work at the construction sites can be monitored through the single image taken using the single camera.

정부의 중·소형 민간공사장 안전관리 강화대책 발표에 따라 CCTV 설치 의무화 대상이 대형 공사장에서 중·소형 공사장으로 확대되었다. 하지만 기존의 건설현장의 CCTV는 안전관리를 위한 단순 관제용으로 활용되고 있어 건설현장의 모니터링을 위한 연구가 필요하다. 이에 본 연구에서는 단안 카메라를 이용하여 촬영한 단 영상을 기반으로 3개의 소실점(vanishing point)을 계산한 후 내부표정요소 정보를 포함하고 있는 카메라 행렬을 결정하고 기준 객체의 높이를 통해 대상 객체의 높이를 계산하여 정확도를 검증하는 연구를 수행하였다. 단안 카메라 기반의 소실점을 이용한 높이 결정 실험을 통해 별도의 지상기준점 측량 없이 단 영상만으로 대상 객체의 높이를 결정할 수 있었으며, 정확도를 평가한 결과 평균제곱근오차는 ±0.161m로 나타났다. 따라서, 단안 카메라를 이용하여 촬영한 단영상을 통해 건설현장의 공사 진척도를 모니터링할 수 있을 것으로 판단된다.

Keywords

References

  1. Ministry of Land. 2020. Infrastructure and Transport. Construction technology promotion act.
  2. Assadzadeh A, Arashpour M, Bab-Hadiashar A, Ngo T, Li H. 2021. Automatic Far-field Camera Calibration for Construction Scene Analysis. Computer-Aided Civil and Infrastructure Engineering. 1-23.
  3. Cipolla R, Drummond T, Robertson D. 1999. Camera Calibration from Vanishing Points in Image of Architectural Scenes. The British Machin Vision Converence, 99:382-391.
  4. Criminisi A, Zisserman A, Gool LV, Bramble S, Compton D. 1998. A New Approach to Obtain Height Measurements from Video. Proceeding of The International Society for Optical Engineering. 3576:227-238.
  5. He BW, Zhou XL, Li YF. 2011. A New Camera Calibration Method from Vanishing Points in a Vision System. Transactions of the Institute of Measurement and Control. 33(7):806-822. https://doi.org/10.1177/0142331209103040
  6. Lin YT, Lin YC, Han JY. 2018. Automatic Water-level Detection using Single-camera Images with Varied Poses. Measurement. 127:167-174. https://doi.org/10.1016/j.measurement.2018.05.100
  7. Mohr R, Tirggs B. 1996. Projective Geometry for Image Analysis. XVIIIth International Symposium on Photogrammetry & Remote Sensing, Vienna, Austria. 42.
  8. Seedahmed G, Habib A. 2002. Two New Algorithms to Retrieve the Calibration Matrix from the 3-D Projective Camera Model. In the Archives of the International Society of Photogrammetry and Remote Sensing, Commission III, Photogrammetric Computer Vision, Graz, Austria.
  9. Tang CY, Wu YL, Hu PC, Ling HC, Chen WC. 2007. Self-calibration for Metric 3D Reconstruction using Homography. IAPR Conference on Machine Vision Applications. 86-89.
  10. Wang G, Hu Z, Wu F, Tsui HT. 2005. Single View Metrology from Scene Constraints. Image and Vision Computing. 23(9):831-840. https://doi.org/10.1016/j.imavis.2005.04.002