Advertisement

Abstract

We show how to exploit temporal periodicity of moving objects to perform 3D reconstruction. The collection of period-separated frames serve as a surrogate for multiple rigid views of a particular pose of the moving target, thus allowing the use of standard techniques of multiview geometry. We motivate our approach using human motion capture data, for which the true 3D positions of the markers are known. We next apply our approach to image sequences of pedestrians captured with a camcorder. Applications of our proposed approach include 3D motion capture of natural and manmade periodic moving targets from monocular video sequences.

Keywords

Periodic Motion Interest Point Correspondence Problem Structure From Motion Epipolar Geometry 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cutler, R., Davis, L.: Robust real-time periodic motion detection, analysis, and applications. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(8) (2000)Google Scholar
  2. 2.
    Faugeras, O.D.: What can be seen in three dimensions with an uncalibrated stereo rig? In: Sandini, G. (ed.) ECCV 1992. LNCS, vol. 588, pp. 563–578. Springer, Heidelberg (1992)Google Scholar
  3. 3.
    Förstner, W., Gülch, E.: A fast operator for detection and precise location of distinct points, corners and centres of circular features. In: ISPRS Intercommission Workshop, Interlaken (June 1987)Google Scholar
  4. 4.
    François, A.R.J., Medioni, G.G., Waupotitsch, R.: Mirror symmetry \(\Longrightarrow\) 2-view stereo geometry. Image and Vision Computing 21(2), 137–143 (2003)CrossRefGoogle Scholar
  5. 5.
    Gårding, J.: Surface orientation and curvature from differential texture distortion. In: Proc. 5th Int’l Conf. on Computer Vision, Boston, pp. 733–739 (1995)Google Scholar
  6. 6.
    Gross, A.D., Boult, T.E.: Analyzing skewed symmetries. Int’l. Journal of Computer Vision 13(1), 91–111 (1994)CrossRefGoogle Scholar
  7. 7.
    Hartley, R.I., Gupta, R., Chang, T.: Stereo from uncalibrated cameras. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (1992)Google Scholar
  8. 8.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)zbMATHGoogle Scholar
  9. 9.
    Kanade, T.: Recovery of the three-dimensional shape of an object from a single view. Artificial Intelligence 17, 409–460 (1981)CrossRefGoogle Scholar
  10. 10.
    Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions using graph cuts. In: Proc. 6th Int’l Conf. on Computer Vision, Vancouver (2001)Google Scholar
  11. 11.
    Liu, Y., Collins, R.T., Tsin, Y.: Gait sequence analysis using Frieze patterns. In: Proc. 7th Europ. Conf. Comput. Vision (2002)Google Scholar
  12. 12.
    Lowe, D.G.: Demo software: Invariant keypoint detector, http://www.cs.ubc.ca/spider/lowe/keypoints/
  13. 13.
    Koch, R., Pollefeys, M., Van Gool, L.: Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters. Int’l. Journal of Computer Vision 32(1), 7–25 (1999)CrossRefGoogle Scholar
  14. 14.
    Malik, J., Rosenholtz, R.: Computing local surface orientation and shape from texture for curved surfaces. Int’l. Journal of Computer Vision 23(2), 149–168 (1997)CrossRefGoogle Scholar
  15. 15.
    Mikolajczyk, K., Schmid, C.: An affine invariant interest point detector. In: European Conference on Computer Vision, pp. 128–142. Springer, Heidelberg (2002)Google Scholar
  16. 16.
    Song, Y., Goncalves, L., Perona, P.: Unsupervised learning of human motion. IEEE Trans. Pattern Analysis and Machine Intelligence 25(7), 814–827 (2003)CrossRefGoogle Scholar
  17. 17.
    Torr, P.H.S., Murray, D.W.: The development and comparison of robust methods for estimating the fundamental matrix. Int. Journal of Computer Vision 24(3), 271–300 (1997)CrossRefGoogle Scholar
  18. 18.
    Wills, J., Agarwal, S., Belongie, S.: What went where. In: Proc. IEEE Conf. Comput. Vision and Pattern Recognition, vol. 1, pp. 37–44 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Serge Belongie
    • 1
  • Josh Wills
    • 1
  1. 1.Department of Computer Science and EngineeringUniversity of CaliforniaSan Diego, La JollaUSA

Personalised recommendations