A Multi Patch Warping Approach for Improved Stereo Block Matching

Mircea Paul Muresan, Sergiu Nedevschi, Radu Danescu

2017

Abstract

Stereo cameras are a suitable solution for reconstructing the 3D information of the observed scenes, and, because of their low price and ease to set up and operate, they can be used in a wide area of applications, ranging from autonomous driving to advanced driver assistance systems or robotics. Due to the high quality of the results, energy based reconstruction methods like semi global matching have gained a lot of popularity in recent years. The disadvantages of semi global matching are the large memory footprint and the high computational complexity. In contrast, window based matching methods have a lower complexity, and are leaner with respect to the memory consumption. The downside of block matching methods is that they are more error prone, especially on surfaces which are not parallel to the image plane. In this paper we present a novel block matching scheme that improves the quality of local stereo correspondence algorithms. The first contribution of the paper consists in an original method for reliably reconstructing the environment on slanted surfaces. The second contribution consists in the creation of set of local constraints that filter out possible outlier disparity values. The third and final contribution consists in the creation of a refinement technique which improves the resulted disparity map. The proposed stereo correspondence approach has been validated on the KITTI stereo dataset.

References

  1. Antunes, M., Barreto, J. P., Premebida, C. & Nunes, U. Can Stereo Vision Replace A Laser Rangefinder? 2012 Ieee/Rsj International Conference On Intelligent Robots And Systems, 7-12 Oct. 2012 2012. 5183-5190.
  2. Einecke, N. & Eggert, J. Stereo Image Warping For Improved Depth Estimation Of Road Surfaces. Intelligent Vehicles Symposium (Iv), 2013 Ieee, 23-26 June 2013 2013. 189-194.
  3. Einecke, N. & Eggert, J. Block-Matching Stereo With Relaxed Fronto-Parallel Assumption. 2014 Ieee Intelligent Vehicles Symposium Proceedings, 8-11 June 2014 2014. 700-705.
  4. Einecke, N. & Eggert, J. A Multi-Block-Matching Approach For Stereo. 2015 Ieee Intelligent Vehicles Symposium (Iv), June 28 2015-July 1 2015 2015. 585- 592.
  5. Geiger, A., Lenz, P., Stiller, C. & Urtasun, R. 2013. Vision Meets Robotics: The Kitti Dataset. Int. J. Rob. Res., 32, 1231-1237.
  6. Haller, I. & Nedevschi, S. Gpu Optimization Of The Sgm Stereo Algorithm. Intelligent Computer Communication And Processing (Iccp), 2010 Ieee International Conference On, 26-28 Aug. 2010 2010. 197-202.
  7. Haller, I. & Nedevschi, S. 2012. Design Of Interpolation Functions For Subpixel-Accuracy Stereo-Vision Systems. Ieee Transactions On Image Processing, 21, 889-898.
  8. Hirschmuller, H. Accurate And Efficient Stereo Processing By Semi-Global Matching And Mutual Information. 2005 Ieee Computer Society Conference On Computer Vision And Pattern Recognition (Cvpr'05), 20-25 June 2005 2005. 807-814 Vol. 2.
  9. Huang, J., Blanz, V. & Heisele, B. 2002. Face Recognition With Support Vector Machines And 3d Head Models. Pattern Recognition With Support Vector Machines First International Workshop Svm, 2002. 334-341.
  10. Kolmogorov, V. & Zabih, R. 2002. Multi-Camera Scene Reconstruction Via Graph Cuts. In: Heyden, A., Sparr, G., Nielsen, M. & Johansen, P. (Eds.) Computer Vision - Eccv 2002: 7th European Conference On Computer Vision Copenhagen, Denmark, May 28-31, 2002 Proceedings, Part Iii. Berlin, Heidelberg: Springer Berlin Heidelberg.
  11. Muresan, M. P., Negru, M. & Nedevschi, S. Improving Local Stereo Algorithms Using Binary Shifted Windows, Fusion And Smoothness Constraint. Intelligent Computer Communication And Processing (Iccp), 2015 Ieee International Conference On, 3-5 Sept. 2015 2015. 179-185.
  12. Penner, M., Woods, M. & Pitt, D. 2015. A Comparison Of Airborne Laser Scanning And Image Point Cloud Derived Tree Size Class Distribution Models In Boreal Ontario. Forests, 6, 4034.
  13. Ranft, B., Strau, T. & X00df. Modeling Arbitrarily Oriented Slanted Planes For Efficient Stereo Vision Based On Block Matching. 17th International Ieee Conference On Intelligent Transportation Systems (Itsc), 8-11 Oct. 2014 2014. 1941-1947.
  14. Scharstein, D. & Szeliski, R. 2002. A Taxonomy And Evaluation Of Dense Two-Frame Stereo Correspondence Algorithms. International Journal Of Computer Vision, 47, 7-42.
  15. Woodfill, J. I., Gordon, G., Jurasek, D., Brown, T. & Buck, R. The Tyzx Deepsea G2 Vision System, Ataskable, Embedded Stereo Camera. 2006 Conference On Computer Vision And Pattern Recognition Workshop (Cvprw'06), 17-22 June 2006 2006. 126-126.
  16. Yang, Q., Wang, L., Yang, R., Stew, H., X0e, Nius, Nist, D. & X0e 2009. Stereo Matching With Color-Weighted Correlation, Hierarchical Belief Propagation, And Occlusion Handling. Ieee Transactions On Pattern Analysis And Machine Intelligence, 31, 492-504.
  17. Yasir Mohd Mustafah, A. W. A., M.H. Ani December 2012 Object Distance And Size Measurement Using Stereo Vision System.
  18. Zbontar, J. & Lecun, Y. 2015. Stereo Matching By Training A Convolutional Neural Network To Compare Image Patches. Corr, Abs/1510.05970.
Download


Paper Citation


in Harvard Style

Muresan M., Nedevschi S. and Danescu R. (2017). A Multi Patch Warping Approach for Improved Stereo Block Matching . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-227-1, pages 459-466. DOI: 10.5220/0006134104590466


in Bibtex Style

@conference{visapp17,
author={Mircea Paul Muresan and Sergiu Nedevschi and Radu Danescu},
title={A Multi Patch Warping Approach for Improved Stereo Block Matching},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={459-466},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006134104590466},
isbn={978-989-758-227-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)
TI - A Multi Patch Warping Approach for Improved Stereo Block Matching
SN - 978-989-758-227-1
AU - Muresan M.
AU - Nedevschi S.
AU - Danescu R.
PY - 2017
SP - 459
EP - 466
DO - 10.5220/0006134104590466