Error Characterization of the Factorization Approach to Shape and Motion Recovery

  • Zhaohui Sun
  • Visvanathan Ramesh
  • A. Murat Tekalp
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1883)


This paper is focused on error characterization of the factorization approach to shape and motion recovery from image sequence using results from matrix perturbation theory and covariance propagation for linear models. Given the 2-D projections of a set of points across multiple image frames and small perturbation on image coordinates, first order perturbation and covariance matrices for 3-D affine/Euclidean shape and motion are derived and validated with the ground truth. The propagation of the small perturbation and covariance matrix provides better understanding of the factorization approach and its results, provides error sensitivity information for 3-D affine/Euclidean shape and moton subject to small image error. Experimental results are demonstrated to support the analysis and show how the error analysis and error measures can be used.


Covariance Matrice Error Characterization Measurement Matrix Covariance Propagation Motion Error 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    C. Tomasi and T. Kanade. Shape and motion from image streams under orthography: A factorization method. International Journal on Computer Vision, 9(2):137–154, November 1992.Google Scholar
  2. 2.
    Joseph L. Mundy and Andrew Zisserman. Geometric Invariance in Computer Vision. The MIT Press, Cambridge, MA, 1992.Google Scholar
  3. 3.
    D. Weinshall and C. Tomasi. Linear and incremental acquisition of invariant shape models from image sequences. IEEE Trans. Pattern Analysis Machine Intelligence, 17(5):512–517, May 1995.Google Scholar
  4. 4.
    C.J. Poelman and T. Kanade. A paraperspective factorization method for shape and motion recovery. IEEE Trans. Pattern Analysis Machine Intelligence, 19(3):206–218, March1997.Google Scholar
  5. 5.
    L. Quan. Self-calibration of an affine camera from multiple views. International Journal on Computer Vision, 19(1):93–105, July 1996.Google Scholar
  6. 6.
    P. Sturm and B. Triggs. A factorization based algorithm for multi-image projective structure and motion. In Computer Vision-ECCV’96, volume 1065, pages II:709–720. Springer Verlag, Lecture Notes in Computer Science, 1996.Google Scholar
  7. 7.
    T. Morita and T. Kanade. A sequential factorization method for recovering shape and motion from image streams. IEEE Trans. Pattern Analysis Machine Intellgence, 19(8):858–867, August1997.Google Scholar
  8. 8.
    L. Quan and T. Kanade. Affine structure from line correspondences with uncalibrated affine cameras. IEEE Trans. Pattern Analysis Machine Intelligence, 19(8):834–845, August 1997.Google Scholar
  9. 9.
    Daniel D. Morris and Takeo Kanade. A unified factorization algorithm for points, line segments and planes with uncertainty. In International Conference on Computer Vision, pages 696–702, Bombay, India, 1998.Google Scholar
  10. 10.
    J. Weng, T. S. Huang, and N. Ahuja. Motion and structure from two perspective views: Algorithms, error analysis and error estimation. IEEE Trans. Pattern Analysis Machine Intelligence, PAMI-11(5):451–476, May 1989.Google Scholar
  11. 11.
    J. Weng, N. Ahuja, and T.S. Huang. Optimal motion and structure estimation. IEEE Trans. Pattern Analysis Machine Intelligence, 15(9):864–884, September 1993.Google Scholar
  12. 12.
    C. Tomasi and J. Zhang. Is structure-from-motion worth pursuing. In Seventh International Symposium on Robotics Research, 1995.Google Scholar
  13. 13.
    K. Daniilidis and M. Spetsakis. Understanding noise sensitivity in structure from motion. In Y. Aloimonos editor, Visual Navigation, pages 61–88. Lawrence Erlbaum Associates, Hillsdale, NJ, 1996.Google Scholar
  14. 14.
    J. H. Wilkinson. The Algebraic Eigenvalue Problem. Clarendon Press, Oxford, England, 1965.zbMATHGoogle Scholar
  15. 15.
    Gene H. Golub and C. F. van Loan. Matrix computations. Johns Hopkins University Press, Baltimore, Maryland, 1996.zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Zhaohui Sun
    • 1
  • Visvanathan Ramesh
    • 2
  • A. Murat Tekalp
    • 1
  1. 1.Dept. of Electrical and Computer EngineeringUniversity of RochesterRochesterUSA
  2. 2.Imaging & Visualization DepartmentSiemens Corporate ResearchPrincetonUSA

Personalised recommendations