Skip to main content
Log in

Structure from Motion Using Sequential Monte Carlo Methods

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

In this paper, the structure from motion (SfM) problem is addressed using sequential Monte Carlo methods. A new SfM algorithm based on random sampling is derived to estimate the posterior distributions of camera motion and scene structure for the perspective projection camera model. Experimental results show that challenging issues in solving the SfM problem, due to erroneous feature tracking, feature occlusion, motion/structure ambiguity, mixed-domain sequences, mismatched features, and independently moving objects, can be well modeled and effectively addressed using the proposed method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Adiv, G. 1989. Inherent ambiguities in recovering 3-D motion and structure from a noisy flow field. IEEE Trans. on Pattern Analysis and Machine Intelligence, 11(5):477–489.

    Google Scholar 

  • Azarbayejani, A. and Pentland, A. 1995. Recursive estimation of motoin, structure, and focal length. IEEE Trans. on Pattern Analysis and Machine Intelligence, 17:562–575.

    Google Scholar 

  • Broida, T.J., Chandrashekhar, S., and Chellappa, R. 1990. Recursive estimation of 3-D kinematics and structure from a noisy monocular image sequence. IEEE Trans. on Aerospace and Electronic Systems, 26:639–656.

    Google Scholar 

  • Chiuso, A., Favaro, P., Jin, H., and Soatto, S. 2002. Motion and structure causally integrated over time. IEEE Trans. on Pattern Analysis and Machine Intelligence, 24:523–535.

    Google Scholar 

  • Daniilidis, K. and Nagel, H. 1993. The coupling of rotation and translation in motion estimation of planar surfaces. In IEEE Computer Vision and Pattern Recognition, New York, NY, pp. 188–193.

  • Dellaert, F., Seitz, S., Thorpe, C., and Thrun, S. 2000. Structure from motion without correspondence. In IEEE Computer Vision and Pattern Recognition, Hilton Head, SC.

  • Dempster, A.P., Laird, N.M., and Rubin, D.B. 1977. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society B, 39:1–38.

    Google Scholar 

  • Doucet, A., Freitas, N., and Gordon, N. 2001. Sequential Monte Carlo Methods in Practice. Springer-Verlag: New York.

    Google Scholar 

  • Faugeras, O. 1993. Three-Dimensional Computer Vision: A Geometric Viewpoint. MIT Press.

  • Forsyth, D., Ioffe, S., and Haddon, J. 1999. Bayesian structure from motion. In International Conference on Computer Vision. Corfu, Greece, pp. 660–665.

  • Gordon, N., Salmon, D., and Smith, A. 1993. Novel approach to nonlinear/ non-gaussian bayesian state estimation. IEE Proceedings, 140:107–113.

    Google Scholar 

  • Hartley, H.O. 1958. Maximum likelihood from incomplete data. Biometrics, 14:174–194.

    Google Scholar 

  • Hartley, R. and Zisserman, A. 2000. Multiple View Geometry. Cambridge, UK: Cambridge University Press.

    Google Scholar 

  • Huang, T. and Netravali, A. 1994. Motion and structure from feature correspondences: A review. Proceedings of the IEEE, 82(2):252–268.

    Google Scholar 

  • Isard, M. and Blake, A. 1996. Contour tracking by stochastic propagation of conditional density. In European Conference on Computer Vision, Cambridge, UK, vol. I, pp. 343–356.

    Google Scholar 

  • Jebara, T., Azarbayejani, A., and Pentland, A. 1999. 3-D structure from 2D motion. IEEE Signal Processing Magazine, 16:66–84.

    Google Scholar 

  • Jerian, C. and Jain, R. 1991. Structure from motion:Acritical analysis of methods. IEEE Trans. Systems, Man and Cybernetics, 21:572–588.

    Google Scholar 

  • Kitagawa, G. 1996. Monte Carlo filter and smoother for non-Gaussian nonlinear state space models. Journal of Computational and Graphical Statistics, 5(1):1–25.

    Google Scholar 

  • Kong, A., Liu, J.S., and Wong, W.H. 1994. Sequential imputation method and Bayesian missing data problems. Journal of the American Statistical Association, 89:278–288.

    Google Scholar 

  • Liu, J.S. and Chen, R. 1998. Sequential monte carlo methods for dynamic systems. J. Amer. Statist. Assoc., 93:1032–1044.

    Google Scholar 

  • Longuet-Higgins, H. 1981. A computer algorithm for reconstructing a scene from two projections. Nature, 293:133–135.

    Google Scholar 

  • Oliensis, J. 2000. A critique of structure from motion algorithms. Technical Report www.neci.nj.com/~homepages/oliensis/ poleiccv.ps, NEC Research Institute, Princeton, NJ.

    Google Scholar 

  • Qian, G., Chellappa, R., and Zheng, Q. 2001. Robust structure from motion estimation using inertial data. Journal of the Optical Society of America A, 18:2982–2997.

    Google Scholar 

  • Soatto, S. and Brockett, R. 1998. Optimal structure from motion: Local ambiguities and global estimates. In IEEE Computer Vision and Pattern Recognition, Santa Barbara, CA, pp. 282–288.

  • Soatto, S. and Perona, P. 1998. Reducing structure-from-motion: A general framework for dynamic vision Part 1: Modeling. IEEE Trans. on Pattern Analysis and Machine Intelligence, 20(9):933–942.

    Google Scholar 

  • Tian, T., Tomasi, C., and Heeger,D. 1996. Comparison of approaches to egomotion computation. In IEEE Computer Vision and Pattern Recognition, San Francisco, CA, pp. 315–320.

  • Tomasi, C. and Kanade, T. 1992. Shape and motion from image streams under orthography: A factorization method. International Journal of Computer Vision, 9(2):137–154.

    Google Scholar 

  • Tomasi, C. and Shi, J. 1994. Good features to track. In IEEE Computer Vision and Pattern Recognition, Seattle, WA, pp. 593–600.

  • Wu, T., Chellappa, R., and Zheng, Q. 1995. Experiments on estimating egomotion and structure parameters using long monocular image sequences. International Journal of Computer Vision, 15:77–103.

    Google Scholar 

  • Young, G. and Chellappa, R. 1992, Statistical analysis of inherent ambiguities in recovering 3-D motion from a noisy flowfield. IEEE Trans. on Pattern Analysis and Machine Intelligence, 14(10):995–1013.

    Google Scholar 

  • Zhang, Z. 1996. Determining the epipolar geometry and its uncertainty: A review. Technical report, French National Institute for Research in Computer Science and Control (INRIA) No. 2927.

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Qian, G., Chellappa, R. Structure from Motion Using Sequential Monte Carlo Methods. International Journal of Computer Vision 59, 5–31 (2004). https://doi.org/10.1023/B:VISI.0000020669.68126.4b

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/B:VISI.0000020669.68126.4b

Navigation