Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

Railway Object Recognition Using Mobile Laser Scanning Data

모바일 레이저 스캐닝 데이터로부터 철도 시설물 인식에 관한 연구

  • ;
  • 좌윤석 (요크대학교 지리정보공학과) ;
  • 손건호 (요크대학교 지리정보공학과) ;
  • 원종운 (한국철도기술연구원) ;
  • 이석 (한국철도기술연구원)
  • Received : 2014.03.10
  • Accepted : 2014.04.11
  • Published : 2014.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

The objective of the research is to automatically recognize railway objects from MLS data in which 9 key objects including terrain, track, bed, vegetation, platform, barrier, posts, attachments, powerlines are targeted. The proposed method can be divided into two main sub-steps. First, multi-scale contextual features are extracted to take the advantage of characterizing objects of interest from different geometric levels such as point, line, volumetric and vertical profile. Second, by considering contextual interactions amongst object labels, a contextual classifier is utilized to make a prediction with local coherence. In here, the Conditional Random Field (CRF) is used to incorporate the object context. By maximizing the object label agreement in the local neighborhood, CRF model could compensate the local inconsistency prediction resulting from other local classifiers. The performance of proposed method was evaluated based on the analysis of commission and omission error and shows promising results for the practical use.

본 연구는 MLS 데이터로부터 자동으로 철도 시설물들을 인식하여 시설물 간의 기하학적인 공간정보를 추출하는데 기여 하고자 한다. 본 연구에서 제안된 방법은 9개 주요 철도 시설물(노반, 레일, 철로, 수목, 플렛폼, 방음벽, 철주, 절연체, 고압선)들의 분류를 목적으로 하고 있다. 이를 위해 제안된 방법은 크게 두 단계로 나뉘어 진행된다. 첫 번째 단계에서는 포인트, 라인, 체적과 수직 프로파일 레벨에서 데이터의 맥락 특징(contextual feature)들이 추출된다. 두 번째 단계에서는 CRF(Conditional Random Field)가 맥락 분류자(contextual classifier)로 사용되어 각 데이터 포인트에 객체 정보가 할당되고 철도 시설물들이 분류된다. 사용된 CRF 모델은 다른 맥락 분류자 와는 달리 로컬지역에서 데이터들의 분류정보가 일관성을 유지하게 하는 장점이 있다. 제안된 방법의 성능은 commission과 omission 오류분석을 통해 입증되었다.

Keywords

References

  1. M. Neubert, R. Hecht, C. Gedrange, M. Trommler, H. Herold, T. Kruger, F. Brimmer, "Extraction of Railroad Objects from Very High Resolution Helicopter-borne LiDAR and Ortho-image Data", International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 38, No. 4, pp. 25-30, 2008.
  2. B. Beger, C. Gedrange, R. Hecht, M. Neubert, "Data Fusion of Extremely High Resolution Aerial Imagery and LiDAR Data for Automated Railroad Centre Line Recontruction", ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 66, No. 6, pp. 40-51, 2011. https://doi.org/10.1016/j.isprsjprs.2011.09.012
  3. J. Yoon, M. Sagong, J. Lee, K. Lee, "Feature Extraction of a Concrete Tunnel Liner from 3D Laser Scanning Data", NDT&E International, Vol. 42, No. 2, pp. 97-105, 2009. https://doi.org/10.1016/j.ndteint.2008.10.001
  4. S. Pu, M. Rutzinger, G. Vosselman, S. Oude Elberink, "Recognizing Basic Structures from Mobile Laser Scanning Data for Road Inventory Studies", ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 66 No. 6, pp. 28-39, 2011. https://doi.org/10.1016/j.isprsjprs.2010.08.003
  5. A. Golovinskiy, V. G. Kim, T. Funkhouser, "Shape-based Recognition of 3D Point Clouds in Urban Environments", Computer Vision, pp. 1-8, 2009.
  6. K. Ishikawa, F. Tonomura, Y. Amano, T. Hashizume, "Recognition of Road Objects from 3D Mobile Mapping Data", International Journal of CAD/CAM, Vol. 13, No. 2, pp. 41-48, 2013.
  7. J. Siegemund, D. Pfeiffer, U. Franke, W. Forstner, "Curb Reconstruction using Conditional Random Fields", 2010 IEEE Intelligent Vehicles Symposium, pp. 203-210, 2010.
  8. H. B. Kim, G. Sohn, "3D Classification of Power-line Scene from Airborne Laser Scanning Data using Random Forest", International Archives of Photogrammetry and Remote Sensing, Vol. 38, No. 3A, pp. 126-132, 2010.
  9. G. Sohn, I. Dowman, "A Model-based Approach for Reconstructing Terrain Surface from Airborne LiDAR Data", Photogrammetric Record, Vol. 22, No. 119, pp. 170-193, 2008.
  10. N. Chehata, L. Guo, C. Mallet, "Airborne LiDAR Feature Selection for Urban Classification Using Random Forests", International Archives of Photogrammetry and Remote Sensing, Vol. 38, No. 3, pp. 207-212, 2009.
  11. E. H. Lim, S. David, "3D Terrestrial LiDAR Classifications with Super-voxels and Multi-scale Conditional Random Fields", Computer-Aided Design, Vol. 41, No.10, pp. 701-710, 2009. https://doi.org/10.1016/j.cad.2009.02.010
  12. C. Luo, G. Sohn, "Line-based Classification of Terrestrial Laser Scanning Data using Conditional Random Field", International Archives of Photogrammetry and Remote Sensing, Vol. 40, No. 7, pp. 155-160, 2013.
  13. S. Kumar, M. Hebert, "Discriminative Random Fields", International Journal of Computer Vision, Vol. 68, No.2, pp. 179-201, 2006. https://doi.org/10.1007/s11263-006-7007-9
  14. D. C. Liu, J. Nocedal, "On the Limited Memory BFGS method for Large Scale Optimization", Mathematical Programming, Vol. 45, No. 1-3, pp. 503-528, 1989. https://doi.org/10.1007/BF01589116
  15. S. V. N. Vishwanathan, N. N. Schraudolph, M. W. Schmidt, K. P. Murphy, "Accelerated Training of Conditional Random Fields with Stochastic Gradient Methods", 23rd International Conference on Machine Learning, pp. 969-976, 2006.