Journal of the Institute of Electronics Engineers of Korea CI (전자공학회논문지CI)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Registration Technique of Partial 3D Point Clouds Acquired from a Multi-view Camera for Indoor Scene Reconstruction

실내환경 복원을 위한 다시점 카메라로 획득된 부분적 3차원 점군의 정합 기법

  • 김세환 (광주과학기술원 정보통신공학과) ;
  • 우운택 (광주과학기술원 정보통신공학과)
  • Published : 2005.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, a registration method is presented to register partial 3D point clouds, acquired from a multi-view camera, for 3D reconstruction of an indoor environment. In general, conventional registration methods require a high computational complexity and much time for registration. Moreover, these methods are not robust for 3D point cloud which has comparatively low precision. To overcome these drawbacks, a projection-based registration method is proposed. First, depth images are refined based on temporal property by excluding 3D points with a large variation, and spatial property by filling up holes referring neighboring 3D points. Second, 3D point clouds acquired from two views are projected onto the same image plane, and two-step integer mapping is applied to enable modified KLT (Kanade-Lucas-Tomasi) to find correspondences. Then, fine registration is carried out through minimizing distance errors based on adaptive search range. Finally, we calculate a final color referring colors of corresponding points and reconstruct an indoor environment by applying the above procedure to consecutive scenes. The proposed method not only reduces computational complexity by searching for correspondences on a 2D image plane, but also enables effective registration even for 3D points which have low precision. Furthermore, only a few color and depth images are needed to reconstruct an indoor environment.

본 논문에서는 실내환경의 3차원 복원을 위해 다시점 카메라부터 획득된 부분적인 3차원 점군에 대한 정합 기법을 제안한다. 일반적으로, 기존의 정합 방법들은 많은 계산량을 요하며, 정합하는데 많은 시간이 소요된다 또한, 상대적으로 정밀도가 낮은 3차원 점군에 대해서는 정합이 어렵다. 이러한 문제점을 해결하기 위해 투영 기반 정합 방법을 제안한다. 첫 번째, 시간적 특성을 기반으로 변화량이 큰 3차원 점들을 제거하고, 공간적 특성을 이용하여 현재 화소의 주변 3차원 점을 참조하여 빈 영역을 채움으로써 깊이 영상 정제 과정을 수행한다. 두 번째, 연속된 두 장면에서의 3차원 점군을 동일한 영상 평면으로 투영하고, 두 단계 정수 매핑을 적용한 후 수정된 KLT (Kanade-Lucas-Tomasi) 특징 추적기를 사용해 대응점을 찾는다. 그리고 적응적 탐색 영역에 기반하여 거리 오차를 최소화함으로써 정밀한 정합을 수행한다. 마지막으로, 대응되는 점들에 대한 색을 참조하여 최종적인 색을 계산하고, 위의 과정을 연속된 장면에 적용함으로써 실내환경을 복원한다. 제안된 방법은 대응점을 2차원 영상 평면에서 찾음으로써 계산의 복잡도를 줄이며, 3차원 데이터의 정밀도가 낮은 경우에도 정합이 효과적이다. 또한, 다시점 카메라를 이용함으로써 몇 장면에 대한 색과 깊이 영상만으로도 실내환경의 3차원 복원이 가능하다.

Keywords

References

  1. Besl, P. J. and McKay, N. D., 'A method for registration of 3D shapes,' IEEE Transaction on Pattern Analysis lind Machine Intelligence, Vol. 14, pp. 239-256, 1992 https://doi.org/10.1109/34.121791
  2. A. Johnson and S. Kang, 'Registration and Integration of Textured 3-D Data,' Tech. report CRL96/4, Digital Equipment Corporation, Cambridge Research Lab, 1996
  3. S. Kang and R. Szeliski, '3-D scene data recovery using omnidirectional multibaseline stereo,' Tech. report CRL-95-6, Oct 1995
  4. G. Blais and M.D.Levine, 'Registering multiview range data to create 3-D computer objects,' IEEE Trans. PAMI, vol. 17, no. 8, pp. 820-824, 1995 https://doi.org/10.1109/34.400574
  5. M. Levoy, K. Pulli, B.Curless, S. Rusinkiewicz, D. Koller, L. Pereira, M. Ginzton, S. Anderson, J. Davis, J. Ginsberg, J. Shade, and D. Fulk. 'The digital Michelangelo project: 3D scanning of large statues,' SIGGRAPH'00, pp. 131-144, July 2000 https://doi.org/10.1145/344779.344849
  6. T. Kanade and P. Rander, 'Virtualized Reality: Constructing Virtual Worlds from Real Scenes,' IEEE MultiMedia, vol.4, no.1, pp.34-47, Jan.-Mar. 1997 https://doi.org/10.1109/93.580394
  7. K. Nishino and K. Ikeuchi, 'Robust Simultaneous Registration of Multiple Range Images Comprising A Large Number of Points,' ACCV2002, 2002
  8. Kari Pulli, Surface Reconstruction and Display from Range and Color Data, Ph.D. dissertation, University of Washington, 1997
  9. G. C. Sharp, S. W. Lee and D. K Wehe, 'Invariant Features and the Registration of Rigid Bodies,' IEEE Int'l Conf., on Robotics and Automation, pp. 932-937, 1999 https://doi.org/10.1109/ROBOT.1999.772424
  10. VIDERE DESIGN, http://www.videredesign.com/, 2004
  11. R. Tsai, 'A versatile camera calibration technique for high-accuracy 3d machine vision metrology using off-the-shelf tv cameras and lenses,' IEEE Journal of Robotics and Automation, vol. 3, no. 4, pp. 323-344, 1987 https://doi.org/10.1109/JRA.1987.1087109
  12. K. Kim and W. Woo, 'Multi-view Camera Tracking for Modeling of Indoor Environment,' Lecture Notes in Computer Science 3331, pp. 288-297, 2004 https://doi.org/10.1007/b104114
  13. S. Kim, K. Kim and W. Woo, 'Projection-based Registration using Color and Texture Information for Virtual Environment Generation,' Lecture Notes in Computer Science 3331, pp. 434-443, 2004 https://doi.org/10.1007/b104114
  14. B. S. Manjunath, W. Y. Ma, 'Texture Features for Browsing and Retrieval of Image Data,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.10, Aug, 1996 https://doi.org/10.1109/34.531803
  15. R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, March 2004