Skip to main content
Log in

A robust method for the reconstruction of disparity maps based on multilevel processing of stereo color image pairs

  • Technical Physics
  • Published:
Doklady Physics Aims and scope Submit manuscript

Abstract

A novel method for the reconstruction of disparity maps (DMs) with robust properties to nonideal registration conditions, reflections, and noise in stereo color image pairs has been substantiated for the first time. The novel approach proposes a scheme for image DM reconstruction where Jaccard distance metric is used as a proximity criterion in stereo image pair matching. A physical interpretation of the method that allows the quality of the formed DMs to be improved significantly is given. A processing block diagram has been developed in accordance with the novel approach. Simulations of the novel DM reconstruction method have shown an advantage of the proposed DM reconstruction scheme in terms of generally recognized criteria, such as the structural similarity index measure and the bad matching pixels, and when visually comparing the formed DMs.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. E. Ramos-Diaz, V. Kravchenko, and V. Ponomaryov, EURASIP J. Adv. Signal Process. 41 (1), 106 (2011) (http://asp.eurasipjournals.com/content/2011/1/106).

    Article  ADS  Google Scholar 

  2. V. F. Kravchenko, V. I. Ponomaryov, and V. I. Pustovoit, Dokl. Phys. 56 (9), 479 (2011).

    Article  ADS  Google Scholar 

  3. V. F. Kravchenko, V. I. Ponomaryov, and V. I. Pustovoit, Dokl. Phys. 59 (11), 507 (2014).

    Article  ADS  Google Scholar 

  4. V. Gonzalez-Huitron, E. Ramos-Diaz, V. Kravchenko, and V. Ponomaryov, Lect. Note Comp. Sci. 8827, 982 (2014).

    Article  Google Scholar 

  5. V. F. Kravchenko, V. I. Ponomaryov, and V. I. Pustovoit, Dokl. Phys. 60 (11), 495 (2015).

    Article  ADS  Google Scholar 

  6. V. Huitron and V. Ponomayov, IEEE Lat. Amer.Trans. 14 (6), 2968 (2016).

    Article  Google Scholar 

  7. A. Geiger, M. Roser, and R. Urtasun, Lect. Note Comp. Sci 6492, 25 (2011).

    Article  Google Scholar 

  8. P. Felzenszwalb and D. Huttenlocher, Int. J. Comp. Vis. 70 (1), 41 (2006).

    Article  Google Scholar 

  9. V. Kolmogorov and R. Zabih, in Eighth IEEE Int. Conf. Comp. Vis. (ICCV 2001), Zurich, Vol. 2, pp. 508–515.

    Article  Google Scholar 

  10. Z. Wang and A. Bovik, IEEE Signal Process. Mag. 26 (1), 98 (2009).

    Article  ADS  Google Scholar 

  11. D. Scharstein, H. Hirschmaller, Y. Kitajima, G. Krathwohl, N. Nesic, X. Wang, and P. Westling, in German Conf. Pattern Recognition (GCPR 2014), Munster, 2014, pp. 1–12.

    Google Scholar 

  12. http://vision.middlebury.edu/stereo/data (November 2013).

  13. M. Peris, S. Martull, A. Maki, Y. Ohkawa, K. Fukui, in 21st Int. Conf. Pattern Recognition (ICPR2012), Tstukaba, 2012, pp. 1038–1042.

    Google Scholar 

  14. S. Martull, M. Martonell, and K. Fukui, in 21st Int. Conf. Pattern Recognition (ICPR2012), Tsukaba, 2012, pp. 40–44.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to V. I. Ponomaryov.

Additional information

Original Russian Text © V.F. Kravchenko, V.I. Ponomaryov, V.I. Pustovoit, S.N. Sadovnychiy, 2017, published in Doklady Akademii Nauk, 2017, Vol. 475, No. 5, pp. 514–518.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kravchenko, V.F., Ponomaryov, V.I., Pustovoit, V.I. et al. A robust method for the reconstruction of disparity maps based on multilevel processing of stereo color image pairs. Dokl. Phys. 62, 374–378 (2017). https://doi.org/10.1134/S1028335817080043

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1028335817080043

Navigation