DOI QR코드

DOI QR Code

Projective Reconstruction from Multiple Images using Matrix Decomposition Constraints

행렬 분해 제약을 사용한 다중 영상에서의 투영 복원

  • 안호영 (인천대학교 컴퓨터공학과) ;
  • 박종승 (인천대학교 컴퓨터공학과)
  • Received : 2011.09.30
  • Accepted : 2012.04.30
  • Published : 2012.06.30

Abstract

In this paper, we propose a novel structure recovery algorithm in the projective space using image feature points. We use normalized image feature coordinates for the numerical stability. To acquire an initial value of the structure and motion, we decompose the scaled measurement matrix using the singular value decomposition. When recovering structure and motion in projective space, we introduce matrix decomposition constraints. In the reconstruction procedure, a nonlinear iterative optimization technique is used. Experimental results showed that the proposed method provides proper accuracy and the error deviation is small.

본 논문에서는 다중 영상에서 추출된 특징점을 사용해서 투영 공간에서의 카메라 행렬과 3차원 정점좌표를 계산하는 방법을 제안한다. 수치적인 안정성을 위해서 특징점을 정규화한 후 복원하며 얻어지는 카메라 행렬과 3차원 정점에 대해서 비정규화한다. 카메라 행렬과 3차원 정점의 초기값을 얻기 위해서 특이값 분해기법을 사용해서 투영 깊이가 적용된 측정 행렬을 분해한다. 행렬 분해 제약을 사용하여 카메라 행렬과 3차원 정점을 투영 복원한다. 투영 복원 과정에서는 비선형 반복적 최적화 방법이 사용된다. 실험 결과 제안방법은 대체로 적절한 정확성을 얻었고 오차의 편차가 크지 않았다.

Keywords

References

  1. R. Hartley and A. Zisserman, Multiple View Geometry, 2nd ed., Cambridge University Press, Cambridge, UK, 2003.
  2. R. Hartley, "Projective Reconstruction and Invariants from Multiple Images," IEEE Trans. PAMI , Vol.16, No.10, pp. 1036-1041, 1994. https://doi.org/10.1109/34.329005
  3. A. Heyden and K. Astrom, "A Canonical Framework for Sequences of Images," Proc. IEEE Workshop on Representation of Visual Scenes, pp. 45-52, 1995.
  4. Q.-T Luong and T. Vieville, "Canonic Representations for the Geometries of Multiple Projective Views," Computer Vision and Image Understanding, Vol.64, No.2, pp. 193-229, 1996. https://doi.org/10.1006/cviu.1996.0055
  5. C. Tomasi and T. Kanade, "Shape and Motion from Image Streams Under Orthography: Factorization Approach," International J ournal of Computer Vision, Vol.9, No.2, pp. 137-154, 1992. https://doi.org/10.1007/BF00129684
  6. C. Tomasi and T. Kanade, "Shape and Motion from Image Streams: a Factorization Method," Proc. Natl. Acad. Sci., Vol.90, pp. 9795-9802, 1993. https://doi.org/10.1073/pnas.90.21.9795
  7. P. Sturm and B. Triggs, "A Factorization Based Algorithm for Multi-Image Projective Structure and Motion," ECCV'96, Vol.2, pp. 709-720, 1996.
  8. B. Triggs. "Factorization Methods for Projective Structure and Motion," CVPR'96, pp. 845-851, 1996.
  9. 박종승, 윤종현, "개선된 직교분해기법을 사용한 빠른 구조 복원 및 융합," 멀티미디어학회논문지, 제10권 제3호, pp. 303-315, 2007.
  10. G. Chen and G. Medioni, "Practical Algorithms for Stratified Structure-from-motion," Image and Vision Computing, Vol.20, No.2, pp. 103-123, 2002. https://doi.org/10.1016/S0262-8856(01)00090-7
  11. Q. Chen and G. Medioni, "Efficient Iterative Solution to M-View Projective Reconstruction Problem," International Journal of Compute Vision and Pattern Recognition, Vol.66, No.3, pp. 2055-2061, 1999.
  12. B. Triggs, P. McLauchlan, R. Hartley, and A. Fitzgibbon, "Bundle Adjustment - A Modern Synthesis," ICCV'99, pp. 298-372, 2000.
  13. S. Mahamud, M. Hebert, Y. Omori, and J. Ponce, "Provably-Convergent Iterative Methods For Projective Structure From Motion," CVPR, Vol.1, pp. 1018-1025, 2001.
  14. S. Mahamud and M. Hebert, "Iterative Projective Reconstruction from Multiple Views," CVPR'2000, pp. 430-437, 2000.
  15. W. Tang and Y. Hung, "A Factorization-based method for Projective Reconstruction with Minimization of 2D Reprojection Errors," Proc. of the 24th DAGM Symposium on Pattern Recognition, pp. 387-394, 2002.
  16. P. McLauchlan and D. Murray, "A Unifying Framework for Structure and Motion Recovery from Image Sequences," ICCV'95, pp. 314-320, 1995.
  17. S. Soatto and P. Perona, "Dynamic Rigid Motion Estimation from Weak Perspective," ICCV'95, pp. 321-328, 1995.
  18. A. Heyden, R. Berthilsson, and G. Sparr, "An Iterative Factorization Method for Projective Structure and Motion from Image Sequences," Image and Vision Computing, Vol.17, No.13, pp. 981-991, 1999. https://doi.org/10.1016/S0262-8856(99)00002-5
  19. G. Sparr, "Simultaneous Reconstruction of Scene Structure and Camera Locations from Uncalibrated Image Sequences," ICPR'96, pp. 328-333, 1996.
  20. W. Tang and Y. Hung, "A Column-space Approach to Projective Reconstruction," Journal Computer Vision and Image Understanding, Vol.101, No.3, pp. 166-176, 2006. https://doi.org/10.1016/j.cviu.2005.07.007
  21. H. Ackermann and K. Kanatani, "Iterative Low Complexity Factorization for Projective Reconstruction," Proc. of RobVis'08, pp. 153- 164, 2008.
  22. A. Heyden, "Projective Structure and Motion from Image Sequences using Subspace Methods," Proc. of the 10th Scandinavian Conference on Image Analysis, pp. 963-968, 1997.
  23. W. Tang and Y. Hung, "A Subspace Method for Projective Reconstruction from Multiple Images with Missing Data," Image and Vision Computing, Vol.24, No.5, pp. 515-524, 2006. https://doi.org/10.1016/j.imavis.2006.02.003
  24. J. Oliensis and R. Hartley, "Iterative Extensions of the Sturm/Triggs Algorithm: Convergence and Nonconvergence," IEEE Trans. PAMI , Vol.29, No.12, pp. 2217-2233, 2007. https://doi.org/10.1109/TPAMI.2007.1132
  25. Y. Dai, H. Li, and M. He, "Element-wise Factorization for N-view Projective Reconstruction," ECCV, pp. 396-409, 2010.
  26. R. Hartley, "In Defence of the 8-point Algorithm," ICCV'95, pp. 1064-1070, 1995.
  27. W. Chojnacki, M. Brooks, A. Hengel, and D. Gawley, "Revisiting Hartley's Normalized Eight-Point Algorithm," IEEE Trans. PAMI , Vol.25, No.9, pp. 1172-1177, 2003. https://doi.org/10.1109/TPAMI.2003.1227992
  28. H. Gavin, The Levenberg-Marquardt Method for Nonlinear Least Squares Curve-fitting Problems, Duke University, pp. 1-15, 2010.
  29. M. Lourakis, "A Brief Description of the Levenberg-Marquardt Algorithm Implemented by Levmar," Foundation for Research and Technology, Vol.4, pp. 1-5, 2005.
  30. R. Berthilsson, A. Heyden, and G. Sparr, "Recursive Structure and Motion from Image Sequences using Shape and Depth Spaces," CVPR'97, pp. 444-449, 1997.