SPARSE WINDOW LOCAL STEREO MATCHING

Sanja Damjanović, Luuk J. Spreeuwers, Ferdinand van der Heijden

2011

Abstract

We propose a new local algorithm for dense stereo matching of gray images. This algorithm is a hybrid of the pixel based and the window based matching approach; it uses a subset of pixels from the large window for matching. Our algorithm does not suffer from the common pitfalls of the window based matching. It successfully recovers disparities of the thin objects and preserves disparity discontinuities. The only criterion for pixel selection is the intensity difference with the central pixel. The subset contains only pixels which lay within a fixed threshold from the central gray value. As a consequence of the fixed threshold, a low-textured windows will use a larger percentage of pixels for matching, while textured windows can use just a few. In such manner, this approach also reduces the memory consumption. The cost is calculated as the sum of squared differences normalized to the number of the used pixels. The algorithm performance is demonstrated on the test images from the Middlebury stereo evaluation framework.

References

  1. Belhumeur, P. N. (1996). A Bayesian approach to binocular stereopsis. Int. J. Comput. Vision, 19(3):237-260.
  2. Cox, I. J. (1994). A maximum likelihood n-camera stereo algorithm. In In IEEE Conf. on Computer Vision and Pattern Recognition, pages 733-739.
  3. Damjanovic, S., van der Heijden, F., and Spreeuwers, L. J. (2009). A new likelihood function for stereo matching: how to achieve invariance to unknown texture, gains and offsets? In VISIGRAPP 2009, International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Lisboa, Portugal, pages 603-608, Lisboa. INSTICC Press.
  4. Hosni, A., Bleyer, M., Gelautz, M., and Rhemann, C. (2010). Geodesic adaptive support weight approach for local stereo matching. In Computer Vision Winter Workshop 2010, pages 60-65.
  5. Lu, J., Lafruit, G., and Catthoor, F. (2007). Fast variable center-biased windowing for high-speed stereo on programmable graphics hardware. In ICIP (6), pages 568-571.
  6. Marr, D. and Poggio, T. (1979). A computational theory of human stereo vision. Proceedings of the Royal Society of London, B-204:301-328.
  7. Mattoccia, S. (2009). A locally global approach to stereo correspondence. In 3DIM09, pages 1763-1770.
  8. Zitnick, C. L. and Kanade, T. (2000). A cooperative algorithm for stereo matching and occlusion detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(7):675-684.
Download


Paper Citation


in Harvard Style

Damjanović S., J. Spreeuwers L. and van der Heijden F. (2011). SPARSE WINDOW LOCAL STEREO MATCHING . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011) ISBN 978-989-8425-47-8, pages 689-693. DOI: 10.5220/0003369106890693


in Bibtex Style

@conference{visapp11,
author={Sanja Damjanović and Luuk J. Spreeuwers and Ferdinand van der Heijden},
title={SPARSE WINDOW LOCAL STEREO MATCHING},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011)},
year={2011},
pages={689-693},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003369106890693},
isbn={978-989-8425-47-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011)
TI - SPARSE WINDOW LOCAL STEREO MATCHING
SN - 978-989-8425-47-8
AU - Damjanović S.
AU - J. Spreeuwers L.
AU - van der Heijden F.
PY - 2011
SP - 689
EP - 693
DO - 10.5220/0003369106890693