Journal of the Institute of Electronics Engineers of Korea SP (대한전자공학회논문지SP)

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

Fundamental Matrix Estimation and Key Frame Selection for Full 3D Reconstruction Under Circular Motion

회전 영상에서 기본 행렬 추정 및 키 프레임 선택을 이용한 전방향 3차원 영상 재구성

  • Kim, Sang-Hoon (Dept. of Image Engineering, GSAIM, Chung-Ang University) ;
  • Seo, Yung-Ho (Dept. of Image Engineering, GSAIM, Chung-Ang University) ;
  • Kim, Tae-Eun (Dept. of Multimedia, NamSeoul University) ;
  • Choi, Jong-Soo (Dept. of Image Engineering, GSAIM, Chung-Ang University)
  • 김상훈 (중앙대학교 첨단영상대학원 영상공학과) ;
  • 서융호 (중앙대학교 첨단영상대학원 영상공학과) ;
  • 김태은 (남서울대학교 멀티미디어학과) ;
  • 최종수 (중앙대학교 첨단영상대학원 영상공학과)
  • Published : 2009.03.25
Download PDF
⟨ Previous Next ⟩

Abstract

The fundamental matrix and key frame selection are one of the most important techniques to recover full 3D reconstruction of objects from turntable sequences. This paper proposes a new algorithm that estimates a robust fundamental matrix for camera calibration from uncalibrated images taken under turn-table motion. Single axis turntable motion can be described in terms of its fixed entities. This provides new algorithms for computing the fundamental matrix. From the projective properties of the conics and fundamental matrix the Euclidean 3D coordinates of a point are obtained from geometric locus of the image points trajectories. Experimental results on real and virtual image sequences demonstrate good object reconstructions.

본 논문은 회전 테이블에서 취득된 영상으로부터 카메라 교정을 위한 강건한 기본 행렬을 계산하기 위한 새로운 알고리즘과 적은 수의 영상만을 이용하는 키 프레임 선택 알고리즘을 통해서 전방향 3차원 영상 재구성 시스템을 구현하였다. 비 교정영상에서 3차원 영상 재구성을 위해서는 카메라 교정 작업이 필수이다. 카메라 교정 과정은 기본 행렬로부터 추정 할 수 있는데, 정확한 기본 행렬의 추정이 선행되어야 한다. 단일 축 회전 움직임은 몇 가지 고정된 특성을 가지고 있는데, 이러한 특성은 영상간의 아웃라이어를 제거하는데 이용되고, 기본 행렬을 구하기 위한 새로운 알고리즘을 제공한다. 또한 제안한 키 프레임 선택 알고리즘을 통해서 선택된 영상의 사영 행렬을 정렬 시킨 다음, 재구성된 3차원 데이터들을 정합시킴으로서 전방향 3차원 영상 재구성을 구현한다. 자체 제작한 영상 취득 시스템(Potonovo)을 통해서 취득한 실제 영상을 대상으로 기존의 기본 행렬 방법 및 키프레임 선택 방법들과 비교 실험을 통하여 제안된 방법들이 더 우수함을 확인하였다.

Keywords

References

  1. E.Boyer, "Object Models from contour Sequences," In Proc. European Conference on Computer Vision, pp.109-118, 1996 https://doi.org/10.1007/3-540-61123-1_131
  2. A.W Fizgibbon, G. Cross, and A. Zisserman, "Automatic 3D Model Construction for Turn-table Sequences," Proc. European Workshop SMILE'98, pp.155-170, 1998 https://doi.org/10.1007/3-540-49437-5_11
  3. P.R.S. Mendonc¸a, K.-Y.K. Wong, and R. Cipolla. "Camera pose estimation and reconstruction from image profiles under circular motion," European Conf. on Computer Vision, vol. II, pp. 864-877, 2000
  4. P. Beardsley, P. H. S. Torr, and A. Zisserman, "3DModel Acquisition from Extended Image Sequences," Proc. 4th European Conference on Computer Vision, 683-695, 1996. https://doi.org/10.1007/3-540-61123-1_181
  5. Luong Q, Faugeras O, "Self-Calibration of a Moving Camera from Point Correspondences and Fundamental Matrices," Int. Jour. of Computer vision, 22(3), 261-289, 1998
  6. Zhengyou Zhang, "A Flexible New Techinque for Camera Calibration," IEEE Transaction on Pattern Analysis and Machine Intelligence, vol.22, no.11, pp.1-20, 2000 https://doi.org/10.1109/TPAMI.2000.824818
  7. Hartely R, "Kruppa's Equations Derived from the fundamental Matrix," IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(2), 133-135, 1997 https://doi.org/10.1109/34.574792
  8. G. Jiang, H.T. Tsui, L. Quan, and A. Zisserman, "Single Axis Geometry by Fitting Conics," Proc. European Conf. Computer Vision, pp. 537-550, 2002 https://doi.org/10.1007/3-540-47969-4_36
  9. P.R.S. Mendoca, K.-Y.K Wong, and R. Cipolla, "Epipolar Geometry from Profiles under Circular Motion," IEEE Trans. Pattern Analysis and Machine Intelligence, 23(6), 604-616, June 2001 https://doi.org/10.1109/34.927461
  10. O.D. Faugeras, L. Quan and P. Sturm, "Self-calibration of a 1D projective camera and its application to the self-calibration of a 2D projective camera," European Conf. on Computer Vision, Vol. I, pp. 36-52, 1998 https://doi.org/10.1007/BFb0055655
  11. G. Jiang, L. Quan, and H.T. Tsui, "Circular Motion Geometry by Minimal 2 Points in 4 Images," IEEE International Conference on Computer Vision, 221-227, 2003 https://doi.org/10.1109/ICCV.2003.1238345
  12. P.D. Sampson, "Fitting conic sections to 'very scattered' data: An iterative refinement of the Bookstein algorithm," Computer Vision, Graphics and Image Processing, vol. 18, pp. 97-108, 1982 https://doi.org/10.1016/0146-664X(82)90101-0
  13. F. Bookstein. "Fitting conic sections to scattered data," Computer Vision, Graphics and Image Processing, vol. 9, pp. 56-71, 1979 https://doi.org/10.1016/0146-664X(79)90082-0
  14. Z.Zhang, "Determining the epipolar geometry and its uncertainty: A review" Int. Journal of computer Vision, 27(2): 161-195, 1998 https://doi.org/10.1023/A:1007941100561
  15. Hartely R, "In Defense of the 8-point Algorithm," IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(6), 580-593, 1997 https://doi.org/10.1109/34.601246
  16. R. Hartly, A. Zisserman "Multiple view geometry in computer vision" Oxford university press, 2000
  17. R. Deriche, Z. Zhang, Q.T. Luong and O.D. Faugeras, "Robust Recovery of the Epipolar Geometry for an Uncalibrated Stereo Rig," ECCV94, 567-576, 1994 https://doi.org/10.1007/3-540-57956-7_64
  18. Csurka G, Zeller C, Zhang Z, Faugeras O, "Characterizing the Uncertainty of the Fundamantal Matrix," INRIA, 1995
  19. Q.-T. Luong and O.D. Faugeras, "The Fundamental matrix: theory, algorithms, and stability analysis," International Journal of Computer Vision, pp. 43-76, 1996 https://doi.org/10.1007/BF00127818
  20. M. A. Fischler and R. C. Bolles, "Random sample consensus: a paradigm for model fitting with application to image analysis and automated cartography," Communication Association and Computing Machine, 24(6), pp.381-395, 1981 https://doi.org/10.1145/358669.358692
  21. Pollefeys, M., Gool, L.V., Vergauwen, M., Cornelis, K., Verbiest, F., Tops, J.: Video-to-3d. In: Proceedings of Photogrammetric Computer Vision 2002 (ISPRS Commission III Symposium), International Archive of Photogrammetry and Remote Sensing. Volume 34. (2002) 252–258
  22. P. Torr, A. Fitzgibbon, A. Zisserman, "The problem of degeneracy in structure and motion (133)recovery from uncalibrated images," International Journal of Computer Vision 32(1): 27–44, Aug 1999 https://doi.org/10.1023/A:1008140928553
  23. S. Gibson, J. Cook, T. Howard, R. Hubbold, D. Oram, "Accurate camera calibration for off-line, video-based augmented reality" In: IEEE and ACM International Symposium on Mixed and Augmented Reality (ISMAR 2002), Darmstadt, Germany(2002)
  24. C. Lei, F. Wu, Z. Hu, and H.T. Tsui, "A new approach to. solving kruppa equations for camera self-calibration," in. Proc. of the 16th Int. Conf. on Pattern Recognition, vol. 2, pp. 308–311, 2002