Anisotropic Median Filtering for Stereo Disparity Map Refinement

Nils Einecke, Julian Eggert

Abstract

In this paper we present a novel method for refining stereo disparity maps that is inspired by both simple median filtering and edge-preserving anisotropic filtering. We argue that a combination of these two techniques is particularly effective for reducing the fattening effect that typically occurs for block-matching stereo algorithms. Experiments show that the newly proposed post-refinement can propel simple patch-based algorithms to much higher ranks in theMiddlebury stereo benchmark. Furthermore, a comparison to state-of-the-artmethods for disparity refinement shows a similar accuracy improvement but at only a fraction of the computational effort. Hence, this approach can be used in systems with restricted computational power.

References

  1. Banno, A. and Ikeuchi, K. (2009). Disparity map refinement and 3D surface smoothing via directed anisotropic diffusion. In 3DIM Workshop, pages 1870 - 1877.
  2. Chen, W., Zhang, M., and Xiong, Z. (2009). Segmentationbased stereo matching with occlusion handling via region border constrains. CVIU.
  3. Einecke, N. and Eggert, J. (2010). A two-stage correlation method for stereoscopic depth estimation. In DICTA, pages 227-234.
  4. Fua, P. (1993). A parallel stereo algorithm that produces dense depth maps and preserves image features. Machine Vision and Applications, 6(1):35-49.
  5. Heo, Y. S., Lee, K. M., and Lee, S. U. (2008). Illumination and camera invariant stereo matching. In CVPR, pages 1-8.
  6. Hirschmüller, H. (2005). Accurate and efficient stereo processing by semi-global matching and mutual information. In CVPR, pages II: 807-814.
  7. Hoare, C. A. R. (1961). Algorithm 65: Find. Communication of the ACM, 4(7):321-322.
  8. Humenberger, M., Zinner, C., Weber, M., Kubinger, W., and Vincze, M. (2010). A fast stereo matching algorithm suitable for embedded real-time systems. CVIU, 114(11):1180-1202.
  9. Lucas, B. D. and Kanade, T. (1981). An iterative image registration technique with an application to stereo vision. In IJCAI, pages 674-679.
  10. Matthies, L., Kanade, T., and Szeliski, R. (1989). Kalman filter-based algorithms for estimating depth from image sequences. IJCV, 3(3):209-238.
  11. Mattoccia, S. (2009). A locally global approach to stereo correspondence. In 3DIM Workshop, pages 1763- 1770.
  12. Mattoccia, S. (2010). Fast locally consistent dense stereo on multicore. In ECVW, pages 69-76.
  13. Perona, P. and Malik, J. (1990). Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell., 12(7):629-639.
  14. Perreault, S. and Hébert, P. (2007). Median filtering in constant time. IEEE Transactions on Image Processing, 16(9):2389-2394.
  15. Scharstein, D. and Szeliski, R. (2002). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IJCV, 47(1-3):7-42.
  16. Sun, D., Roth, S., and Black, M. J. (2010). Secrets of optical flow estimation and their principles. In CVPR, pages 2432-2439.
  17. Sun, X., Mei, X., Jiao, S., Zhou, M., and Wang, H. (2011). Stereo matching with reliable disparity propagation. In 3DIMPVT, pages 132-139.
  18. Tian, Q. and Huhns, M. N. (1986). Algorithms for subpixel registration. CVGIP, 35(2):220-233.
  19. Wang, L., Liao, M., Gong, M., Yang, R., and Nister, D. (2006). High-quality real-time stereo using adaptive cost aggregation and dynamic programming. In 3DPVT, pages 798-805.
  20. Yang, Q., Yang, R., Davis, J., and Nistér, D. (2007). Spatialdepth super resolution for range images. In CVPR, pages 1-8.
  21. Yoon, K.-J. and Kweon, I. S. (2006). Adaptive supportweight approach for correspondence search. IEEE Trans. Pattern Anal. Mach. Intell., 28:650-656.
  22. Zabih, R. and Woodfill, J. (1994). Non-parametric local transforms for computing visual correspondence. In ECCV, pages 151-158.
Download


Paper Citation


in Harvard Style

Einecke N. and Eggert J. (2013). Anisotropic Median Filtering for Stereo Disparity Map Refinement . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-48-8, pages 189-198. DOI: 10.5220/0004200401890198


in Bibtex Style

@conference{visapp13,
author={Nils Einecke and Julian Eggert},
title={Anisotropic Median Filtering for Stereo Disparity Map Refinement},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={189-198},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004200401890198},
isbn={978-989-8565-48-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)
TI - Anisotropic Median Filtering for Stereo Disparity Map Refinement
SN - 978-989-8565-48-8
AU - Einecke N.
AU - Eggert J.
PY - 2013
SP - 189
EP - 198
DO - 10.5220/0004200401890198