DOI QR코드

DOI QR Code

Matching for Cylinder Shape in Point Cloud Using Random Sample Consensus

Random Sample Consensus를 이용한 포인트 클라우드 실린더 형태 매칭

  • Received : 2015.10.29
  • Accepted : 2016.02.18
  • Published : 2016.05.15

Abstract

Point cloud data can be expressed in a specific coordinate system of a data set with a large number of points, to represent any form that generally has different characteristics in the three-dimensional coordinate space. This paper is aimed at finding a cylindrical pipe in the point cloud of the three-dimensional coordinate system using RANSAC, which is faster than the conventional Hough Transform method. In this study, the proposed cylindrical pipe is estimated by combining the results of parameters based on two mathematical models. The two kinds of mathematical models include a sphere and line, searching the sphere center point and radius in the cylinder, and detecting the cylinder with straightening of center. This method can match cylindrical pipe with relative accuracy; furthermore, the process is rapid except for normal estimation and segmentation. Quick cylinders matching could benefit from laser scanning and reverse engineering construction sectors that require pipe real-time estimates.

포인트 클라우드 데이터는 어떠한 형태를 표현하기 위해 무수히 많은 점들을 갖는 데이터 집합으로 특정 벡터 시스템에서 표현될 수 있으며, 일반적으로 3차원 좌표 공간에서 다양한 특성을 갖게 된다. 본 논문은 3차원 좌표 시스템의 포인트 클라우드에서 기존 방법(Hough Transform)보다 빠른 실린더 형태의 파이프 추정을 목표로 한다. 이를 위해 비교적 빠른 RANdom SAmple Consensus(RANSAC)를 사용한다. 본 논문에서 제안하는 실린더 형태의 파이프 추정은 두 가지 형태의 수학적 모델을 근거로 파라미터를 계산하고, 결과를 조합하여 예측한다. 두 가지 수학적 모델은 구(Sphere)와 직선(Line)이며, RANSAC 적합을 통해 실린더의 축과 반지름이 될 수 있는 구의 파라미터(중심과 반지름)를 계산하고, 이를 직선화하여 실린더를 추정한다. 이는 법선 추정(Normal Estimation) 및 분할(Segmentation) 없이 비교적 정확도를 유지하며, 빠르게 실린더 매칭을 할 수 있게 한다. 빠른 실린더 매칭은 실시간 파이프 추정이 필요한 레이저 스캐닝 및 건설 역설계 분야에서 활용할 수 있을 것이다.

Keywords

References

  1. Rabbani. Tahir, Frank van den Heuvel, and G. Vosselmann, "Segmentation of point clouds using smoothness constraint," International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 36.5 pp. 248-253, 2006.
  2. Abuzaina. Anas, Mark S. Nixon, and John N. Carter, "Sphere detection in kinect point clouds via the 3d hough transform," In Computer Analysis of Images and Patterns, Springer Berlin Heidelberg, pp. 290-297, 2013.
  3. Zhang. Ning, "Plane Fitting on Airborne Laser Scanning Data Using RANSAC," Lunds Tekniska Hogskola, 2011.
  4. Garcia. Sergio, "Fitting primitive shapes to point clouds for robotic grasping," Master of Science Thesis. School of Computer Science and Communication, Royal Institute of Technology, Stockholm, Sweden, 2009.
  5. Su. Yun-Ting, and James Bethel, "Detection and robust estimation of cylinder features in point clouds," Proc. of ASPRS Annual Conference on Opportunities for Emerging Geospatial Technologies, 2010.
  6. JONES. Brian, and Michel AOUN, "Learning 3D Point Cloud Histograms," 2009.
  7. Fischler. Martin A, and Robert C. Bolles, "Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography," Communications of the ACM 24, No. 6, pp. 381-395, 1981. https://doi.org/10.1145/358669.358692
  8. Raguram. Rahul, Jan-Michael Frahm, and Marc Pollefeys, "A comparative analysis of RANSAC techniques leading to adaptive real-time random sample consensus," Computer Vision-ECCV 2008, Springer Berlin Heidelberg, pp. 500-513. 2008.
  9. Smith. Lindsay I, "A tutorial on principal components analysis," Cornell University, USA 51, 2002.
  10. Person. K, "On Lines and Planes of Closest Fit to System of Points in Space," Philosophical Magazine, Vol. 2, pp. 559-572, 1901. https://doi.org/10.1080/14786440109462720