GROWING AGGREGATION ALGORITHM FOR DENSE TWO-FRAME STEREO CORRESPONDENCE

Elisabetta Binaghi, Ignazio Gallo, Chiara Fornasier, Mario Raspanti

2006

Abstract

This work aims at defining a new method for matching correspondences in stereoscopic image analysis. The salient aspects of the method are -an explicit representation of occlusions driving the overall matching process and the use of neural adaptive technique in disparity computation. In particular, based on the taxonomy proposed by Scharstein and Szelinsky, the dense stereo matching process has been divided into three tasks: matching cost computation, aggregation of local evidence and computation of disparity values. Within the second phase a new strategy has been introduced in an attempt to improve reliability in computing disparity. An experiment was conducted to evaluate the solutions proposed. The experiment is based on an analysis of test images including data with a ground truth disparity map.

References

  1. Barnard, S.T. and Fischler, M.A. 1982.Computational Stereo. ACM Computing Surveys, 14(4):553-572.
  2. Barnard, T. and Thompson W.B. 1980. Disparity Analysis of Images. IEEE Trans. PAMI :333-340.
  3. Bishop, C.M.1995. Neural Networks for Pattern Recognition, Oxford University Press, Oxford.
  4. Bobik, A. F and Intille, S. S.. 1999. Large occlusion stereo. International Journal on Computer Vision, 33, 181-200.
  5. Cox, J.I., S.L. Higonani, S.P. Rao, B.M. Maggs. 1996. A Maximum Likelihoods Stereo Algorithm. Computer Vision and Image Understanding, 63, 542-567.
  6. Dhond, U.R. and Aggarwal, J.K. 1989. Structure from Stereo - a review. IEEE Trans. On Systems, Man, and Cybernetics, 19, 1489-1510.
  7. Hannah, M.J. 1989. A system for digital stereo image matching. Photogrammetric Engineering and Remote Sensing, 55, 1765-1770.
  8. McMillan, L. and Bishop, G. 1995. Plenoptic modelling:An image-based rendering system. Computer Graphics (SIG-GRAPH'95), 39-46.
  9. Kanade, T.and Okutomi, M. 1994. A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment. IEEE Trans. on PAMI, 16(9), 920-932.
  10. Pao, Y.H..1989. Adaptive Pattern Recognition and Neural Networks. Addison Wesley, MA.
  11. Rumelhart, H., G.E.Hinton, and R.J.Williams. 1986. Learning Internal Representation by Error Propagation, in Rumelhart H., McClelland J.L.(eds.), Parallel Distributed Processing, 318-362. MIT Press, Cambridge, MA.
  12. Scharstein, D. and Szeliski R. 2002. A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms. International Journal of Computer Vision, 47, 7-42.
Download


Paper Citation


in Harvard Style

Binaghi E., Gallo I., Fornasier C. and Raspanti M. (2006). GROWING AGGREGATION ALGORITHM FOR DENSE TWO-FRAME STEREO CORRESPONDENCE . In Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 972-8865-40-6, pages 326-332. DOI: 10.5220/0001362203260332


in Bibtex Style

@conference{visapp06,
author={Elisabetta Binaghi and Ignazio Gallo and Chiara Fornasier and Mario Raspanti},
title={GROWING AGGREGATION ALGORITHM FOR DENSE TWO-FRAME STEREO CORRESPONDENCE},
booktitle={Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2006},
pages={326-332},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001362203260332},
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 - GROWING AGGREGATION ALGORITHM FOR DENSE TWO-FRAME STEREO CORRESPONDENCE
SN - 972-8865-40-6
AU - Binaghi E.
AU - Gallo I.
AU - Fornasier C.
AU - Raspanti M.
PY - 2006
SP - 326
EP - 332
DO - 10.5220/0001362203260332