LINEAR COMPLEXITY STEREO CORRESPONDENCE - From Interpolation to Segment-based Approach

Vilson Heck Junior, Marcelo Ricardo Stemmer

Abstract

This paper presents the work in progress on the enhancement of a stereo correspondence method based on linear complexity region indexing with an image segmentation method. Such improvement shows itself to achieve better results (compared to its predecessor) when evaluated on Middlebury Stereo Evaluation, keeping the computing complexity O(n) of the algorithmic solution. In spite of the better results, this method still need to solve some issues related to surfaces inclinations. The steps taken to create this improvement, some stereo correspondence results and evaluations are presented.

References

  1. Klaus, A., Sormann, M. and Karner, K. 2006. Segmentbased stereo matching using belief propagation and a self-adapting dissimilarity measure. ICPR 7806 Proceedings of the 18th International Conference on Pattern Recognition.
  2. Murray, D., Little, J. J., 2000. Using Real-Time Stereo Vision for Mobile Robot Navigation. In Autonomous Robots, Volume 8, Number 2. SpringerLink.
  3. Oliveira, M. A. F. de, Wazlavick, R. S., 2005. Linear Complexity Stereo Matching Based on Region Indexing. In Proceedings of the XVIII Brazilian Symposium on Computer Graphics and Image Processing - SIBGRAPI'05, IEEE Computer Society. Natal.
  4. Rehrmann, V., Priese, L. 1997. Fast and Robust Segmentation of Natural Color Scenes. In Proceedings of the 3 rd Asian Conference on Computer Vision. Springer Verlag, pages 598-606.
  5. Scharstein , D., Szeliski, R. 2002. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 47:7-42.
  6. Scharstein , D., Szeliski, R. 2003. High-accuracy stereo depth maps using structured light. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, volume 1, pages 195-202.
  7. Middlebury Stereo Evaluation, 2011. Available at http://vision.middlebury.edu/stereo/eval/.
Download


Paper Citation


in Harvard Style

Heck Junior V. and Ricardo Stemmer M. (2011). LINEAR COMPLEXITY STEREO CORRESPONDENCE - From Interpolation to Segment-based Approach . In Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-989-8425-75-1, pages 308-312. DOI: 10.5220/0003539803080312


in Bibtex Style

@conference{icinco11,
author={Vilson Heck Junior and Marcelo Ricardo Stemmer},
title={LINEAR COMPLEXITY STEREO CORRESPONDENCE - From Interpolation to Segment-based Approach},
booktitle={Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2011},
pages={308-312},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003539803080312},
isbn={978-989-8425-75-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - LINEAR COMPLEXITY STEREO CORRESPONDENCE - From Interpolation to Segment-based Approach
SN - 978-989-8425-75-1
AU - Heck Junior V.
AU - Ricardo Stemmer M.
PY - 2011
SP - 308
EP - 312
DO - 10.5220/0003539803080312