ENERGY-MINIMIZATION BASED MOTION ESTIMATION USING ADAPTIVE SMOOTHNESS PRIORS

Tarik Arici, Vural Aksakalli

Abstract

Energy minimization algorithms are used in low-level computer vision applications for labeling tasks such as stereo-disparity estimation, image restoration, motion estimation, and optical flow. The energy function involves terms that evaluate the goodness of a solution in terms of a prior knowledge in addition to data terms. The most widely used priors are smoothness-based priors, which enhance the quality significantly. However, the smoothness assumption is not valid across discontinuities (e.g. motion boundaries). We present a method to update the weights of smoothness terms using the dual problem when the approximation algorithm is iterative. The dual of the primal energy minimization problem is used to infer about the validity of the smoothness prior and impose it more correctly at each iteration. We demonstrate the effectiveness of this method against the state-of-the-art in the optical flow literature.

References

  1. Boykov, Y. and Veksler, O. (2006). Mathematical Models of Computer Vision: The Handbook, Graph Cuts in Vision and Graphics: Theories and Applications. Dover Publications.
  2. Boykov, Y., Veksler, O., and Zabih, R. (2001). Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(11):1222-1239.
  3. Hofmann, T., Puzicha, J., and Buhmann, J. (1996). Unsupervised segmentation of textured images by pairwise data clustering. In International Conference on Image Processing.
  4. Kohli, P. and Torr, P. (2007). Dynamic graph cuts for efficient inference in markov random fields. Pattern Analysis and Machine Inteligence, 29(12):2079-2088.
  5. Kolmogorov, V. and Boykov, Y. (2002). An experimental comparison of mincut/max-flow algorithms for energy minimization in vision. In Energy Minimization Methods in Computer Vision and Pattern Recognition.
  6. Meltzer, T., Yanover, C., and Weisss, Y. (2005). Globally optimal solutions for energy minimization in stereo vision using reweighted belief propagation. In International Conference on Computer Vision, pages 428- 435.
  7. Papadimitriou, C. H. and Steiglitz, K. (1998). Combinatorial Optimization: Algorithms and Complexity. Dover Publications.
  8. Rav-Acha, A., Kohli, P., Rother, C., and Fitzgibbon, A. (2008). Unwrap mosaics: A new representation for video editing. ACM Transactions on Graphics (SIGGRAPH 2008).
  9. Rav-Acha, A., Pritch, Y., and Peleg, S. (2006). Making a long video short: Dynamic video synopsis. IEEE Conference on Computer Vision and Pattern Recognition.
  10. Veksler, O. (1999). Efficient Graph-Based Energy Minimizatation Methods in Computer Vision. Cornell University.
  11. Weickert, J., Bruhn, A., and Schnorr, C. (2005). Lucas/kanade meets horn/schunck: Combining local and global optic flow methods. International Journal of Computer Vision, 61(3):211-231.
  12. Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., and Bischof, H. (2009). Anisotropic huber-l1 optical flow. In British Machine Vision Conference.
Download


Paper Citation


in Harvard Style

Arici T. and Aksakalli V. (2012). ENERGY-MINIMIZATION BASED MOTION ESTIMATION USING ADAPTIVE SMOOTHNESS PRIORS . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-04-4, pages 201-207. DOI: 10.5220/0003805202010207


in Bibtex Style

@conference{visapp12,
author={Tarik Arici and Vural Aksakalli},
title={ENERGY-MINIMIZATION BASED MOTION ESTIMATION USING ADAPTIVE SMOOTHNESS PRIORS},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={201-207},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003805202010207},
isbn={978-989-8565-04-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2012)
TI - ENERGY-MINIMIZATION BASED MOTION ESTIMATION USING ADAPTIVE SMOOTHNESS PRIORS
SN - 978-989-8565-04-4
AU - Arici T.
AU - Aksakalli V.
PY - 2012
SP - 201
EP - 207
DO - 10.5220/0003805202010207