Extending Interrupted Feature Point Tracking for 3-D Affine Reconstruction

  • Yasuyuki Sugaya
  • Kenichi Kanatani
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3021)


Feature point tracking over a video sequence fails when the points go out of the field of view or behind other objects. In this paper, we extend such interrupted tracking by imposing the constraint that under the affine camera model all feature trajectories should be in an affine space. Our method consists of iterations for optimally extending the trajectories and for optimally estimating the affine space, coupled with an outlier removal process. Using real video images, we demonstrate that our method can restore a sufficient number of trajectories for detailed 3-D reconstruction.


Camera Model Motion Segmentation Outlier Removal Subspace Separation Complete Trajectory 
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.


  1. 1.
    Brandt, S.: Closed-form solutions for affine reconstruction under missing data. In: Proc. Statistical Methods in Video Processing Workshop, Copenhagen, Denmark, June, 2002, pp. 109–114 (2002)Google Scholar
  2. 2.
    Fischer, M.A., Bolles, R.C.: Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Comm. ACM 24(6), 381–395 (1981-1986)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)zbMATHGoogle Scholar
  4. 4.
    Huynh, D.Q., Heyden, A.: Outlier detection in video sequences under affine projection. In: Proc. IEEE Conf. Comput. Vision Pattern Recog., Kauai, HI, U.S.A, December 2001, vol. 2, pp. 695–701 (2001)Google Scholar
  5. 5.
    Jacobs, D.W.: Linear fitting with missing data for structure-from-motion. Comput. Vision Image Understand 82(1), 57–81 (2001)zbMATHCrossRefGoogle Scholar
  6. 6.
    Kahl, F., Heyden, A.: Affine structure and motion from points, lines and conics. Int. J. Comput. Vision 33(3), 163–180 (1999)CrossRefGoogle Scholar
  7. 7.
    Kanatani, K.: Motion segmentation by subspace separation and model selection. In: Proc. 8th Int. Conf. Comput. Vision, Vancouver, Canada, July 2001, vol. 2, pp. 301–306 (2001)Google Scholar
  8. 8.
    Kanatani, K.: Motion segmentation by subspace separation: Model selection and reliability evaluation. Int. J. Image Graphics 2(2), 179–197 (2002)CrossRefGoogle Scholar
  9. 9.
    Kanatani, K.: Evaluation and selection of models for motion segmentation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 335–349. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  10. 10.
    Poelman, C.J., Kanade, T.: A paraperspective factorization method for shape and motion recovery. IEEE Trans. Patt. Anal. Mach. Intell. 19(3), 206–218 (1997)CrossRefGoogle Scholar
  11. 11.
    Rousseeuw, P.J., Leroy, A.M.: Robust Regression and Outlier Detection. Wiley, New York (1987)zbMATHCrossRefGoogle Scholar
  12. 12.
    Saito, H., Kamijima, S.: Factorization method using interpolated feature tracking via projective geometry. In: Proc. 14th British Machine Vision Conf., Norwich, UK, September 2003, vol. 2, pp. 449–458 (2003)Google Scholar
  13. 13.
    Shum, H.-Y., Ikeuchi, K., Reddy, R.: Principal component analysis with missing data and its application to polyhedral object modeling. IEEE Trans. Patt. Anal. Mach. Intell. 17(3), 854–867 (1995)CrossRefGoogle Scholar
  14. 14.
    Sugaya, Y., Kanatani, K.: Outlier removal for motion tracking by subspace separation. IEICE Trans. Inf. Syst. E86-D(6), 1095–1102 (2003)Google Scholar
  15. 15.
    Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography—A factorization method. Int. J. Comput. Vision 9(2), 137–154 (1992)CrossRefGoogle Scholar
  16. 16.
    Tomasi, C., Kanade, T.: Detection and Tracking of Point Features, CMU Tech. Rep. CMU-CS-91-132, (April 1991),

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Yasuyuki Sugaya
    • 1
  • Kenichi Kanatani
    • 1
  1. 1.Depertment of Information TechnologyOkayama UniversityOkayamaJapan

Personalised recommendations