LOCAL MINIMUM DISTANCE FOR THE DENSE DISPARITY ESTIMATION

Eric Alvernhe, Philippe Montesinos, Stefan Janaqi, Min Tang

Abstract

This paper presents a new algorithm to solve the problem of dense disparity map estimation in stereo-vision. Our method is an iterative process inspired by variationnal approach. A new criteria is used as the attachment term based on the distance to local minimum of a similarity measure. Our iterative process is heuristic. Nevertheless, we are able to interpret this algorithm presenting both combinatorial and continuous characteristics. The quality and precision of the results obtained by our method both on image benchmarks and real data clearly demonstrate the the validity of this approach.

References

  1. Alvarez, L., Deriche, R., Sanchez, J., and Weickert, J. (2000). Dense disparity map estimation respecting image discontinuities: a pde and scalespace based approach.
  2. Alvarez, L., F., G., P.L., L., and J.M., M. (1992). Axioms and fundamental equation of image processing. Technical Report 9231, CEREMADE, Université Paris Dauphine, France, Mars 1992. Paru dans Arch. for Rat. Mechanics 123(3), pp 199-257, 1993.
  3. Blomgren, P. (1998). Total Variation Methods for Restoration of Vector Valued Images. PhD thesis, University of California, Los Angeles.
  4. Boufama and Jin (2002). Towards a fast and reliable dense matching algorithm.
  5. Chambolle, A. (1994). Partial differential equation and image processing. IEE Int. Conf. Image Processing, Austin, I:16-20.
  6. Gouet, V., Montesinos, P., and Pelé, D. (1998). Stereo matching of color images using differential invariants. In International Conference on Image Processing, Chicago, USA.
  7. MacQueen, J. (1967). Some methods of classification and analysis of multivaluate observation.
  8. Maier, D., Role, A., Hesser, J., and Manner, R. (2003). Dense disparity maps respecting occlusions and object separation.
  9. Nagel, H. (1983). Constraints for the estimation of deplacement vector fields from image sequences. IJCAI.
  10. N.Slesareva, A.Bruhn, and J.Weickert (2005). Optic flow goes stereo: A variational method for estimating discontinuity-preserving dense disparity maps.
  11. Ohta, Y. and Kanade, T. (1985). Stereo by intra- and interscanline search using dynamic programming.
  12. Scharstein, D., Szeliski, R., and Zabih, R. (2001). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms.
  13. Takeo, K. and Okutomi, M. (1994). A stereo matching algorithm with an adaptative window : theory and experiment.
  14. Torr, P. and Murray, D. (1997). ”the development and comparison of robust methods for estimating the fundamental matrix”. International Journal of Computer Vision, 24(3):271-300.
  15. Zhang, Z., Deriche, R., Faugeras, O., and Luong, Q. (1994). ”a robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry”. Technical Report RR-2273, INRIA Sophia-Antipolis, France.
Download


Paper Citation


in Harvard Style

Alvernhe E., Montesinos P., Janaqi S. and Tang M. (2006). LOCAL MINIMUM DISTANCE FOR THE DENSE DISPARITY ESTIMATION . In Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 972-8865-40-6, pages 341-348. DOI: 10.5220/0001369803410348


in Bibtex Style

@conference{visapp06,
author={Eric Alvernhe and Philippe Montesinos and Stefan Janaqi and Min Tang},
title={LOCAL MINIMUM DISTANCE FOR THE DENSE DISPARITY ESTIMATION},
booktitle={Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2006},
pages={341-348},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001369803410348},
isbn={972-8865-40-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - LOCAL MINIMUM DISTANCE FOR THE DENSE DISPARITY ESTIMATION
SN - 972-8865-40-6
AU - Alvernhe E.
AU - Montesinos P.
AU - Janaqi S.
AU - Tang M.
PY - 2006
SP - 341
EP - 348
DO - 10.5220/0001369803410348