Improved Confidence Measures for Variational Optical Flow

Maren Brumm, Jan Marek Marcinczak, Rolf-Rainer Grigat

2015

Abstract

In the last decades variational optical flow algorithms have been intensively studied by the computer vision community. However, relatively few effort has been made to obtain robust confidence measures for the estimated flow field. As many applications do not require the whole flow field, it would be helpful to identify the parts of the field where the flow is most accurate. We propose a confidence measure based on the energy functional that is minimized during the optical flow calculation and analyze the performance of different data terms. For evaluation, 7 datasets of the Middlebury benchmark are used. The results show that the accuracy of the flow field can be improved by 53.3 % if points are selected according to the proposed confidence measure. The suggested method leads to an improvement of 35.2 % compared to classical confidence measures.

References

  1. Baker, S., Scharstein, D., Lewis, J. P., Roth, S., Black, M. J., and Szeliski, R. (2011). A database and evaluation methodology for optical flow. International Journal of Computer Vision, 92(1):1-31.
  2. Barron, J. L., Fleet, D. J., and Beauchemin, S. S. (1994). Performance of optical flow techniques. International Journal of Computer Vision, 12(1):43-77.
  3. Bruhn, A. and Weickert, J. (2006). A confidence measure for variational optic flow methods. In Geometric Properties for Incomplete Data, pages 283-298. Springer.
  4. Bruhn, A., Weickert, J., and Schnörr, C. (2005). Lucas/Kanade meets Horn/Schunck: Combining local and global optic flow methods. International Journal of Computer Vision, 61(3):211-231.
  5. Horn, B. K. P. and Schunck, B. G. (1981). Determining optical flow. Artificial Intelligence, 17:185-203.
  6. Meyer, Y. (2001). Oscillating patterns in image processing and nonlinear evolution equations: the fifteenth Dean Jacqueline B. Lewis memorial lectures, volume 22. American Mathematical Soc.
  7. Otte, M. and Nagel, H.-H. (1994). Optical flow estimation: advances and comparisons. In Computer Vision ECCV'94, pages 49-60. Springer.
  8. Wedel, A. and Cremers, D. (2011). Stereo Scene Flow for 3D Motion Analysis. Springer.
  9. Zach, C., Pock, T., and Bischof, H. (2007). A duality based approach for realtime TV-L1 optical flow. In Pattern Recognition, pages 214-223. Springer.
Download


Paper Citation


in Harvard Style

Brumm M., Marcinczak J. and Grigat R. (2015). Improved Confidence Measures for Variational Optical Flow . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-091-8, pages 389-394. DOI: 10.5220/0005167203890394


in Bibtex Style

@conference{visapp15,
author={Maren Brumm and Jan Marek Marcinczak and Rolf-Rainer Grigat},
title={Improved Confidence Measures for Variational Optical Flow},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={389-394},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005167203890394},
isbn={978-989-758-091-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)
TI - Improved Confidence Measures for Variational Optical Flow
SN - 978-989-758-091-8
AU - Brumm M.
AU - Marcinczak J.
AU - Grigat R.
PY - 2015
SP - 389
EP - 394
DO - 10.5220/0005167203890394