Korean Journal of Construction Engineering and Management (한국건설관리학회논문집)

Korea Institute of Construction Engineering and Management (한국건설관리학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on 3D Indoor mapping for as-built BIM creation by using Graph-based SLAM

준공 BIM 구축을 위한 Graph-based SLAM 기반의 실내공간 3차원 지도화 연구

  • Jung, Jaehoon (University of Bonn. Department of Photogrammetry) ;
  • Yoon, Sanghyun (School of Civil & Environmental Engineering, Yonsei University) ;
  • Cyrill, Stachniss (University of Bonn. Department of Photogrammetry) ;
  • Heo, Joon (School of Civill & Environmental Engineering, Yonsei University)
  • Received : 2016.01.27
  • Accepted : 2016.03.17
  • Published : 2016.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

In Korea, the absence of BIM use in existing civil structures and buildings is driving a demand for as-built BIM. As-built BIMs are often created using laser scanners that provide dense 3D point cloud data. Conventional static laser scanning approaches often suffer from limitations in their operability due to the difficulties in moving the equipment, the selection of scanning location, and the requirement of placing targets or extracting tie points for registration of each scanned point cloud. This paper aims at reducing the manual effort using a kinematic 3D laser scanning system based on graph-based simultaneous localization and mapping (SLAM) for continuous indoor mapping. The robotic platform carries three 2D laser scanners: the front scanner is mounted horizontally to compute the robot's trajectory and to build the SLAM graph; the other two scanners are mounted vertically to scan the profiles of surrounding environments. To reduce the accumulated error in the trajectory of the platform through loop closures, the graph-based SLAM system incorporates AdaBoost loop closure approach, which is particularly suitable for the developed multi-scanner system providing more features than the single-scanner system for training. We implemented the proposed method and evaluated it in two indoor test sites. Our experimental results show that the false positive rate was reduced by 13.6% and 7.9% for the two dataset. Finally, the 2D and 3D mapping results of the two test sites confirmed the effectiveness of the proposed graph-based SLAM.

현재 국내 대부분의 토목 건축 구조물이 BIM 정보가 부재한 상황에서 준공 BIM(as-built BIM)의 수요가 점차 증가하고 있다. 준공 BIM 구축을 위한 공간자료 취득에는 고밀도의 포인트 클라우드를 생성할 수 있는 레이저 스캐너가 주로 활용되고 있다. 하지만 기존의 고정식 스캔 시스템은 이동이 번거롭고, 정밀한 위치 선정이 필요 하며, 스캔 자료 정합을 위해 별도의 표지를 설치하거나 공액점을 추출하는 과정이 필요하다. 본 연구에서는 수작업을 최소화하기 위해 기존의 고정식 스캔 시스템을 대체할 수 있는 이동식 스캔 시스템을 제안하고자 하며, 기반 기술로 graph-based SLAM을 적용하였다. 테스트 장비는 총 세 개의 2차원 스캐너를 탑재하고 있으며, 중앙의 한 개는 수평으로 설치되어 graph 구축을 통한 이동경로취득에 사용되었고, 좌우 두 개는 수직으로 설치되어 시스템 진행의 연직 방향으로 주변 구조물에 대한 3차원 스캔 정보 취득에 사용되었다. 개발된 graph-based SLAM은 이동경로 상에 누적된 위치오차를 해소하기 위한 loop closure 처리 방법으로 Adaboost 기계학습을 적용하였다. 이는 특히 본 연구에서 사용한 장비와 같이 기계학습을 위한 다수의 feature 정보를 제공할 수 있는 멀티 스캐너 시스템에 적합한 방식이며, 두 실내공간을 대상으로 한 테스트에서 단일 스캐너 대비 false positive rate를 각각 7.9% 및 13.6%까지 줄일 수 있었다. 최종적으로 연구대상지역의 2차원 및 3차원 지도 구축을 통해 개발된 graph-based SLAM의 효용성을 확인하였다.

Keywords

References

  1. Andrade-Cetto, J., Vidal-Calleja, T., and Sanfeliu, A. (2005). "Unscented transformation of vehicle states in SLAM." IEEE International Conference on Robotics and Automation (ICRA), Barcelona, Spain. pp. pp. 323-328.
  2. Arras, K. O. (2003). "Feature-based robot navigation in known and unknown environments." Doctoral thesis, Swiss Federal Institute of Technology Lausanne. p. 206.
  3. Bosse, M., and Zlot, R. (2009). "Keypoint design and evaluation for place recognition in 2D lidar maps." Robotics and Autonomous Systems, 57(12), pp. 1211-1224. https://doi.org/10.1016/j.robot.2009.07.009
  4. Digital times. (2015). "The BIM will affect more than 20% of civil structures in Korea by the year 2020." news paper, http://www.dt.co.kr/contents.html?article_no=2015012202109976753006.
  5. Durrant-Whyte, H., and Bailey, T. (2006). "Simultaneous localization and mapping: part I." Robotics & Automation Magazine, IEEE, 13(2), pp. 99-110.
  6. Eastman, C., Teicholz, P., Sacks, R., and Liston, K. (2011). "BIM handbook: A guide to building information modeling for owners, managers, architects, engineers, contractors, and fabricators." Wiley, Hoboken, NJ. p. 648.
  7. Granstrom, K., Schon, T. B., Nieto, J. I., and Ramos, F. T. (2011). "Learning to close loops from range data." The international journal of robotics research, 30(14), pp. 1728-1754. https://doi.org/10.1177/0278364911405086
  8. Grisetti, G., Kummerle, R., Stachniss, C., and Burgard, W. (2010). "A tutorial on graph-based SLAM." Intelligent Transportation Systems Magazine, IEEE, 2(4), pp. 31-43.
  9. Gutmann, J. S., and Konolige, K. (1999). "Incremental mapping of large cyclic environments. Paper presented at the Computational Intelligence in Robotics and Automation." IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA), California, USA. pp. 318-325.
  10. Hanley, J. A., and McNeil, B. J. (1982). "The meaning and use of the area under a receiver operating characteristic (ROC) curve." Radiology, 143(1), pp. 29-36. https://doi.org/10.1148/radiology.143.1.7063747
  11. Jung, J., Hong, S., Jeong, S., Kim, S., Cho, H., Hong, S., and Heo, J. (2014). "Productive modeling for development of as-built BIM of existing indoor structures." Automation in Construction, 42, pp. 68-77. https://doi.org/10.1016/j.autcon.2014.02.021
  12. Jung, J., Kim, J., Yoon, S., Kim, S., Cho, H., Kim, C., and Heo, J. (2015a). "Bore-Sight Calibration of Multiple Laser Range Finders for Kinematic 3D Laser Scanning Systems." Sensors, 15(5), pp. 10292-10314. https://doi.org/10.3390/s150510292
  13. Jung, J., Yoon, S., Ju, S., and Heo, J. (2015b). "Development of Kinematic 3D Laser Scanning System for Indoor Mapping and As-Built BIM Using Constrained SLAM." Sensors, 15(10), pp. 26430-26456. https://doi.org/10.3390/s151026430
  14. Jung, J., Hong, S., Yoon, S., Kim, J., and Heo, J. (2015c). "Automated 3D Wireframe Modeling of Indoor Structures from Point Clouds Using Constrained Least-Squares Adjustment for As-Built BIM." Journal of Computing in Civil Engineering, 10.1061/(ASCE)CP.1943-5487.0000556, 04015074.
  15. Jung, Y., Kim, Y., Kim, M., and Ju, T. (2013). "Concept and Structure of Parametric Object Breakdown Structure (OBS) for Practical BIM." Korean Journal of Construction Engineering and Management, KICEM, 14(3), pp. 88-96. https://doi.org/10.6106/kJCEM.2013.14.3.088
  16. Kang, D., Zhang, G., and Suh. I. (2011). "Experimental Verification of a Vanishing Point-based Loop Closure Method in a Line-based SLAM under Various Environment." Information and control symposium, Seoul, Korea, pp. 119-120.
  17. Kang, L., Moon, H., Kim, H., and Kwak, J. (2013). "Usability Improvement of BIM for Construction Projects Using Active BIM Fuctions." Korean Journal of Construction Engineering and Management, KICEM, 14(5), pp. 74-83. https://doi.org/10.6106/KJCEM.2013.14.5.074
  18. Kim, R., Choi, H., and Kim, E. (2011). "GraphSLAM improved by removing measurement outliers." Korean Institute of Intelligent Systems, 21(4), pp. 493-498. https://doi.org/10.5391/JKIIS.2011.21.4.493
  19. Kummerle, R., Grisetti, G., Strasdat, H., Konolige, K., and Burgard, W. (2011). "g2o: a general framework for graph optimization." IEEE International Conference on Robotics and Automation (ICRA), Shanghai, China. pp. 3607-3613.
  20. Martinez-Cantin, R., and Castellanos, J. A. (2005). "Unscented SLAM for large-scale outdoor environments." IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Alberta, Canada. pp. 3427-3432.
  21. Neuhaus, F. (2011). "A Full 2D/3D GraphSLAM System for Globally Consistent Mapping based on Manifolds." Doctoral thesis, Universitat Koblenz-Landau. p. 85.
  22. Ochmann, S., Vock, R., Wessel, R., and Klein, R. (2016) . "Automatic reconstruction of parametric building models from indoor point clouds." Computers & Graphics, 54, pp. 94-103. https://doi.org/10.1016/j.cag.2015.07.008
  23. Olson, E. B. (2009). "Real-time correlative scan matching." IEEE International Conference on Robotics and Automation (ICRA), Kobe, Japan. pp. 4387-4393.
  24. Park, H., and Lee, K. (2011). "Pattern Recognition." Ehanmedia. p. 423.
  25. Petersen, K. B., and Pedersen, M. S. (2008). "The matrix cookbook." Technical University of Denmark, p. 15.
  26. Ryu, K. (2012). "Autonomous Robotic Strategies for Urban Search and Rescue." Doctoral thesis , Virginia Polytechnic Institute and State University. p. 109.
  27. Shojaie, K., and Shahri, A. M. (2008). "Iterated unscented SLAM algorithm for navigation of an autonomous mobile robot." International Conference on Intelligent Robots and Systems (IROS), Nice, France, pp. 1582-1587.
  28. Song, J., and Hwang, S. (2014). "Past and state-ofthe-art SLAM technologies." Journal of Institute of Control, Robotics and Systems, 20(3), pp. 372-379. https://doi.org/10.5302/J.ICROS.2014.14.9024
  29. Tang, J., Chen, Y., Jaakkola, A., Liu, J., Hyyppa, J., and Hyyppa, H. (2014). "NAVIS-An UGV Indoor Positioning System Using Laser Scan Matching for Large-Area Real-Time Applications." Sensors, 14(7), pp. 11805-11824. https://doi.org/10.3390/s140711805
  30. Thomson, C., Apostolopoulos, G., Backes, D., and Boehm, J. (2013). "Mobile laser scanning for indoor modelling." ISPRS Workshop Laser Scanning, Antalya, Turkey. pp. 289-293.
  31. Thrun, S., and Montemerlo, M. (2006). "The graph SLAM algorithm with applications to large-scale mapping of urban structures." The International Journal of Robotics Research, 25(5-6), pp. 403-429. https://doi.org/10.1177/0278364906065387
  32. Turner, E. L. (2015). "3D Modeling of Interior Building Environments and Objects from Noisy Sensor Suites." Doctoral thesis, UC Berkeley.
  33. Wang, H., Fu, G., Li, J., Yan, Z. and Bian, X. (2013). "An adaptive UKF based SLAM method for unmanned underwater vehicle." Mathematical Problems in Engineering, 2013, p. 12.
  34. Wong, K.D., and Fan, Q. (2013). "Building information modelling (BIM) for sustainable building design." Facilities, 31(3/4), pp. 138-157. https://doi.org/10.1108/02632771311299412
  35. Yin, J., Carlone, L., Rosa, S., Anjum, M. L., and Bona, B. (2014). "Scan Matching for Graph SLAM in Indoor Dynamic Scenarios." Conference on the 27th International Florida Artificial Intelligence Research Society, Florida, USA. pp. 418-423.