A PDES METHOD PRESERVING BOUNDARIES ON DENSE DISPARITY MAP RECONSTRUCTION

Ji liu, Junjian Peng, Yuechao Wang, Yandong Tang

Abstract

Over smoothness restricts the application of PDEs in the field of dense disparity map reconstruction, because disparity map reconstruction usually requires preserving discontinuousness in some areas such as the boundaries of objects. To preserve disparity discontinuousness, this paper adopts two strategies. Firstly, ground control points (GCPs) are introduced as the soft constraint. Secondly, this paper designs a structure of smoothness part in energy functional, which can preserve discontinuousness effectively. Moreover, the adjustable parameters in the smoothness part advance its robustness. In experiments, we compare proposed method with graph cuts method and prove that PDEs is also a useful solution for disparity map reconstruction and has the advantage of dealing with smooth images.

References

  1. Alvarez, L., Deriche, R., Sanchez, J., Weickert, J., 2000. Dense disparity map estimation respecting image discontinuities: a PDE and scale-space based approach. In Technical Report RR-3874, INRIA.
  2. Alvarez, L., Weickert, J., Sanchez, J., 1999. A scale-space approach to nonlocal optical flow calculations. In Scale-Space Theories in Computer Vision, pages 235- 246.
  3. Aubert, G., Barlaud, M., Faugeras, O. and Jehan-Besson, S., 2002. Image segmentation using active contours: Calculus of variations or shape gradients? In Research Report, INRIA.
  4. Aubert, G., Vese, L., 1997. A variational method in image recovery. In SIAM Journal of Numerical Analysis, volume 34, pages 1948-1979.
  5. Birchfield, S., Tomasi, C., 1999. Multiway cut for stereo and motion with slanted surfaces, Proceeding of International Conference Computer Vision, pages 489- 495.
  6. Boykov, Y., Veksler, O., Zabih R., 2001. Fast approximate Energy Minimization via Graph Cuts. In Proceeding IEEE Transaction Pattern Analysis and Machine Intelligence, volume 23, pages 1222-1239.
  7. Chan, T. F., Vese, L.A., 2001. Active contours without edges. In IEEE Transaction on Image Processing, volume 10, pages 366-277.
  8. Deriche, R., Bouvin, S., Faugeras, O., 1997. A level-set approach for stereo. In Proceeding SPIE, Investigative Image Processing, volume 2092, pages 150-161.
  9. Faugeras, O., Keriven, R., 1998. Complete Dense Stereo vision Using Level Set Methods. In Proceeding European Conference on Computer Vision, pages 379- 394.
  10. Faugeras, O., Keriven, R., 2002. Variational Principles, Surface Evolution, PDE's, Level Set Methods and the Stereo Problem. In IEEE Transaction on Image Processing, volume 7, pages 336-344.
  11. Felzenszwalb, P. F., Huttenlokcher, D. P., 2004. Efficient Belief Propagation for Early Vision. In Proceeding International Journal of Computer Vision, volume 1, pages 261-268.
  12. Frey B. J., Koetter R., Petrovic N., 2002. Very loopy belief propagation for unwrapping phase images. In MIT Press, volume 14.
  13. Kass, M., Witkin, A., Terzopoulos D., 1988. Snakes: active contour models. In International Journal of Computer Visiosn, volume 1, pages 321-331.
  14. Kim, J.C., Lee, K.M., Choi, B.T., Lee, S.U., 2005. A dense stereo matching using two-pass dynamic programming with generalized ground control points. Proceeding Computer Vision and Pattern Recognition, pages 1075-1082
  15. Kim, J., Kolmogorov, V., Zabih, R., 2003. Visual correspondence using energy minimization and mutual information. In Proceeding International Conference Computer Vision, pages 1033-1040.
  16. Klaus, A., Sormann, M., Karner, K, 2006. Segment-based stereo matching using belief propagation and a selfadapting dissimilarity measure, In International Conference of Pattern and Recognition, volume 3, pages 15-18.
  17. Kolmogorov, V., Zabih, R., 2004. What energy functions can be minimized via graph cuts? In IEEE Trans. Pattern Analysis and Machine Intelligence, volume 28, pages 147-159.
  18. Marshall, F. T., William, T. F., 2003. Comparison of Graph Cuts with Belief Propagation for Stereo, using Identical MRF Parameters. In Proceedings of the Ninth IEEE International Conference on Computer Vision, volume 2, pages 900-906.
  19. Maso, G. D., Morel, J. M., Solimini, S., 1992. A variational method in image segmentation: existence and approximation results, In Acta Matematica, volume 168, pages 89-151.
  20. Osher, S., Sethian, J.A., 1988. Fronts propagating with curvature dependent. In Journal of Computational Physics, volume 79, pages 12-49.
  21. Robert, L., Deriche, R., 1996. Dense disparity map reconstruction: A minimization and regularization approach which preserves discontinuities. In Proceeding European Conference on Computer Vision, pages 439-451.
  22. Roy, S., Cox, I., 1998. A maximum-flow formulation of the n-camera stereo correspondence problem. In Proceeding international Conference of Computer Vision, pages 492-498.
  23. Scharstein, D., Szeliski, R., 2002. A taxonomy and evaluation of dense two-frame stereo orrespond- dence algorithms, In International Journal of Computer Vision, volume 47, pages 7-42.
  24. Sun, J., Zheng, N.N., Shum, H.Y., 2003. Stereo Matching Using Belief Propagation. In IEEE Trans. Pattern Analysis and Machine Intelligence, volume 25, pages 787-800.
Download


Paper Citation


in Harvard Style

liu J., Peng J., Wang Y. and Tang Y. (2008). A PDES METHOD PRESERVING BOUNDARIES ON DENSE DISPARITY MAP RECONSTRUCTION . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 655-661. DOI: 10.5220/0001080606550661


in Bibtex Style

@conference{visapp08,
author={Ji liu and Junjian Peng and Yuechao Wang and Yandong Tang},
title={A PDES METHOD PRESERVING BOUNDARIES ON DENSE DISPARITY MAP RECONSTRUCTION},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={655-661},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001080606550661},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - A PDES METHOD PRESERVING BOUNDARIES ON DENSE DISPARITY MAP RECONSTRUCTION
SN - 978-989-8111-21-0
AU - liu J.
AU - Peng J.
AU - Wang Y.
AU - Tang Y.
PY - 2008
SP - 655
EP - 661
DO - 10.5220/0001080606550661