한국정보통신학회논문지 (Journal of the Korea Institute of Information and Communication Engineering)

  • 제20권3호
  • /
  • Pages.527-535
  • /
  • 2016
  • /
  • 2234-4772(pISSN)
  • /
  • 2288-4165(eISSN)
한국정보통신학회 (The Korea Institute of Information and Commucation Engineering)
권호 표지
DOI QR코드

DOI QR Code

3차원 복원을 위한 관측행렬의 불확실성 분석

Uncertainty Analysis of Observation Matrix for 3D Reconstruction

  • 투고 : 2016.01.16
  • 심사 : 2016.02.16
  • 발행 : 2016.03.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

3차원 형상과 모션을 추정하기 위한 통계학적 최적화 알고리즘들이 다양하게 개발되고 있다. 그렇지만 통계적 접근은 카메라의 기하학적 위치나 관측시야각 등의 설정에 따른 SfM(Shape form Motion)의 민감한 영향을 분석하는데는 한계가 있다. 본 논문은 SfM의 모호성을 예측하기 위해 카메라 촬영 구성 요소를 이용하여 관측행렬의 불확실성을 정량적으로 추정할 수 있는 방법을 제안한다. 제안한 방법은 SfM 알고리즘의 최종적인 복원 성능을 예측하는데도 매우 효과적인 방법이다. 또한 합리적인 복원 결과를 기대할 수 있도록 카메라 촬영 구성을 설정하기 위한 직접적인 가이드라인을 제공할 수 있다는 점에서 중요하다. 실험결과는 이러한 카메라 촬영 구성을 이용하여 관측행렬의 불확실성에 대한 정량적 추정을 실험적으로 검증하고 본 알고리즘의 효율성을 확인한다.

Statistical optimization algorithms have been variously developed to estimate the 3D shape and motion. However, statistical approaches are limited to analyze the sensitive effects of SfM(Shape from Motion) according to the camera's geometrical position or viewing angles and so on. This paper propose the quantitative estimation method about the uncertainties of an observation matrix by using camera imaging configuration factors predict the reconstruction ambiguities in SfM. This is a very efficient method to predict the final reconstruction performance of SfM algorithm. Moreover, the important point is that our method show how to derive the active guidelines in order to set the camera imaging configurations which can be expected to lead the reasonable reconstruction results. The experimental results verify the quantitative estimates of an observation matrix by using camera imaging configurations and confirm the effectiveness of our algorithm.

키워드

참고문헌

  1. C. Wu. "Towards linear-time incremental structure from motion," In Proceeding of 2013 International Conference on 3D Vision, pp.127-134, Seattle, USA, Jun. 2013.
  2. P. A. Beardsley, A. Zisserman, and D. W. Murray, "Sequential updating of projective and affine structure from motion," International Journal of Computer Vision, vol.23, no.3, pp.235-259, Jun.-Jul. 1997. https://doi.org/10.1023/A:1007923216416
  3. J. Heller, M. Havlena, M. Jancosek, A. Torii, and T. Pajdla, "3D Reconstruction from Photographs by CMP SfM Web Service," In Proceeding of 14th IAPR International Conference on Machine Vision Applications, Tokyo, Japan, pp. 30-34, May, 2015.
  4. M. Jancosek and T. Pajdla. "Multi-view reconstruction preserving weakly-supported surfaces," In Proceeding of 2011 IEEE Conference on CVPR, pp. 3121-3128, New York, USA, Jun. 2011.
  5. B. Triggs, P. McLauchlan, R. Hartley, and A. Fitzgibbon: "Bundle adjustment-A modern synthesis, in Vision Algorithms: Theory and Practice," Lecture Notes in Computer Science, Springer-Verlag, vol.1883, pp.298-372, Jan. 2000.
  6. J. Oliensis. "The least-squares error for structure from infinitesimal motion," International Journal of Computer Vision, vol.61, no.3, pp.259-299, Feb. 2005. https://doi.org/10.1023/B:VISI.0000045326.88734.8b
  7. Zhaohui Sun, Visvanathan Ramesh, A. Murat Tekalp, "Error Characterization of the Factor-ization method," Computer Vision and Image Understanding. vol.82, no2, pp.110-137, Nov. 2001. https://doi.org/10.1006/cviu.2001.0910
  8. M. Spetsakis, "Models of statistical visual motion estimation," Computer Vision, Graphics, and Image Processing, vol.60, no.3, pp.300-312, Nov. 1994. https://doi.org/10.1006/cviu.1994.1065
  9. K. Daniilidis and H.-H. Nagel, "Analytical results on error sensitivity of motion estimation from two views," Image and Vision Computing, vol.8, no.4, pp.297-303, Nov. 1990. https://doi.org/10.1016/0262-8856(90)80006-F
  10. A. Chiuso, R. Brockett, and S. Soatto. "Optimal structure from motion:Local ambiguities and global estimates," International Journal of Computer Vision, vol.39, no.3, pp.195-228, Sep. 2000. https://doi.org/10.1023/A:1026563712076
  11. G.-S.J. Young and R.: Chellappa, "Statistical analysis of inherent ambiguities in recovering 3-d motion from a noisy flow field," IEEE Transactions on PAMI, vol.14, no.10, pp.995- 1013, Oct. 1992. https://doi.org/10.1109/34.159903
  12. K. Kanatani, "Unbiased estimation and statistical analysis of 3-d rigid motion from two views," IEEE Transactions on PAMI, vol.15, no.1, pp.37-50, Jan. 1993. https://doi.org/10.1109/34.184773
  13. R. Szeliski and S. B. Kang, "Shape ambiguities in structure-from-motion," IEEE Transactions on PAMI, vol.19, no.1, pp.506-512, May 1997. https://doi.org/10.1109/34.589211
  14. J. Oliensis, "A New Structure-from-Motion Ambiguity," IEEE Transactions on PAMI, vol.22, no.7, pp.685-700, Jul. 2000. https://doi.org/10.1109/34.865186
  15. J. Weng, N. Ahuja, and T.S. Huang, "Optimal motion and structure estimation," IEEE Transactions on PAMI, vol.15, no.9, pp.864-884, Sep. 1993. https://doi.org/10.1109/34.232074
  16. C. Tomasi and T. Kanade, "Shape and motion from image streams under orthography: A factorization method," International Journal of Computer Vision, vol.9, no.9, pp.137-154, Nov. 1992. https://doi.org/10.1007/BF00129684
  17. R. Szeliski and S. B. Kang, "Recovering 3D shape and motion from image streams using nonlinear least squares," Journal of Visual Communication and Image Representation, 5, no.1, pp10-28, Mar. 1994. https://doi.org/10.1006/jvci.1994.1002