View-invariant Alignment and Matching of Video Sequences

  title={View-invariant Alignment and Matching of Video Sequences},
  author={Cen Rao and Alexei Gritai and Mubarak Shah and Tanveer F. Syeda-Mahmood},
In this paper, we propose a novel method to establish temporal correspondence between the frames of two videos. 3D epipolar geometry is used to eliminate the distortion generated by the projection from 3D to 2D. Although the fundamental matrix contains the extrinsic property of the projective geometry between views, it is sensitive to noise. Therefore, we propose the use of a rank constraint of corresponding points in two views to measure the similarity between trajectories. This rank… CONTINUE READING
Highly Cited
This paper has 29 citations. REVIEW CITATIONS
21 Citations
13 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 21 extracted citations


Publications referenced by this paper.
Showing 1-10 of 13 references

Feature-based sequenceto-sequence matching

  • Y. Caspi, D. Simakov, M. Irani
  • In VAMODS workshop with ECCV,
  • 2002
3 Excerpts

Autocalibration and euclidean reconstruction using rigid motion of a stereo rig

  • R. Horaud, G. Csurka
  • In ICCV,
  • 1998
1 Excerpt

Similar Papers

Loading similar papers…