ROBUST KEY FRAME EXTRACTION FOR 3D RECONSTRUCTION FROM VIDEO STREAMS

Mirza Tahir Ahmed, Matthew N. Dailey, Jose Luis Landabaso, Nicolas Herrero

2010

Abstract

Automatic reconstruction of 3D models from video sequences requires selection of appropriate video frames for performing the reconstruction. We introduce a complete method for key frame selection that automatically avoids degeneracies and is robust to inaccurate correspondences caused by motion blur. Our method combines selection criteria based on the number of frame-to-frame point correspondences, Torr’s geometrical robust information criterion (GRIC) scores for the frame-to-frame homography and fundamental matrix, and the point-to-epipolar line cost for the frame-to-frame point correspondence set. In a series of experiments with real and synthetic data sets, we show that our method achieves robust 3D reconstruction in the presence of noise and degenerate motion.

References

  1. Blender Artists (2000). 3D church model. Available at http://blenderartists.org/cms/.
  2. Blender Community (2009). Blender [open source software]. Available at http://www.blender.org/.
  3. Hartley, R. and Zisserman, A. (2003). Multiple View Geometry in Computer Vision. Cambridge University Press, New York, NY, USA.
  4. Pollefeys, M. and Van Gool, L. (2002). Visual modeling with a hand held camera. Journal of Visualization and Computer Animation (JVCA), 13:199-209.
  5. Seo, Kim, Doo, and Choi (2008). Optimal keyframe selection algorithm for three-dimensional reconstruction in uncalibrated multiple images. Society of PhotoOptical Instrumentation Engineers (SPOIE), Vol. 47.
  6. Seo, Kim, Jho, and Hong (2003). 3D estimation and keyframe selection for match move. International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC).
  7. Torr, P., Fitzgibbon, A., and Zisserman, A. (1998). Maintaining multiple motion model hypotheses over many views to recover matching and structure. pages 485- 491.
  8. Torr, P. H. S. (1998). Geometric motion segmentation and model selection. Phil. Trans. Royal Society of London A, 356:1321-1340.
Download


Paper Citation


in Harvard Style

Tahir Ahmed M., N. Dailey M., Luis Landabaso J. and Herrero N. (2010). ROBUST KEY FRAME EXTRACTION FOR 3D RECONSTRUCTION FROM VIDEO STREAMS . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-028-3, pages 231-236. DOI: 10.5220/0002836902310236


in Bibtex Style

@conference{visapp10,
author={Mirza Tahir Ahmed and Matthew N. Dailey and Jose Luis Landabaso and Nicolas Herrero},
title={ROBUST KEY FRAME EXTRACTION FOR 3D RECONSTRUCTION FROM VIDEO STREAMS},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={231-236},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002836902310236},
isbn={978-989-674-028-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)
TI - ROBUST KEY FRAME EXTRACTION FOR 3D RECONSTRUCTION FROM VIDEO STREAMS
SN - 978-989-674-028-3
AU - Tahir Ahmed M.
AU - N. Dailey M.
AU - Luis Landabaso J.
AU - Herrero N.
PY - 2010
SP - 231
EP - 236
DO - 10.5220/0002836902310236