Distributed RANSAC for the robust estimation of three-dimensional reconstruction

Author(s): M. Xu and J. Lu
DOI: 10.1049/iet-cvi.2010.0223

For access to this article, please select a purchase option:

Buy article PDF

Buy Knowledge Pack

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership

Recommend Title Publication to library

IET Computer Vision — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Author(s): M. Xu ¹ and J. Lu ^{1, 2}
- Affiliations: 1: Department of Electronic Engineering, Tsinghua University, Beijing, People's Republic of China
  2: EDA Lab, Research Institute of Tsinghua University, Shenzhen, People's Republic of China
Source: Volume 6, Issue 4, July 2012, p. 324 – 333
DOI: 10.1049/iet-cvi.2010.0223 , Print ISSN 1751-9632, Online ISSN 1751-9640

Many low- or middle-level three-dimensional reconstruction algorithms involve a robust estimation and selection step whereby parameters of the best model are estimated and inliers fitting this model are selected. The RANSAC (RANdom SAmple consensus) algorithm is the most widely used robust algorithm for this task. A new version of RANSAC, called distributed RANSAC (D-RANSAC), is proposed, to save computation time and improve accuracy. The authors compare their results with those of classical RANSAC and randomised RANSAC (R-RANSAC). Experiments show that D-RANSAC is superior to RANSAC and R-RANSAC in computational complexity and accuracy in most cases, particularly when the inlier proportion is below 65%.

References

1. 1)
  - P.J. Rousseeuw . A resampling design for computing high-breakdown regression. Stat. Probab. Lett. , 2 , 125 - 128
2. 2)
  - Torr, P., Murray, D.: `Outlier detection and motion segmentation', SPIE Sensor Fusion VI, September 1993, Boston, USA, p. 432–443.
3. 3)
  - Chum, O., Matas, J., Kittler, J.: `Locally optimized RANSAC', Proc. 25th DAGM Symp., 2003, Magdeburg, Germany, p. 236–243.
4. 4)
  - A.R. Dick , P.H.S. Torr , R. Cipolla . Modelling and interpretation of architecture from several images. J. Comput. Vis. , 2 , 111 - 134
5. 5)
  - Frahm, J.M., Pollefeys, M.: `RANSAC for quasi-degenerate data (QDEGSAC)', Proc. CVPR’06, 2006, p. 453–460.
6. 6)
  - Torr, P., Zisserman, A.: `Robust computation and parameterization of multiple view relations', Proc. ICCV, 1998, Bombay, India, p. 727–732.
7. 7)
  - Chum, O., Matas, J.: `Randomized RANSAC with td,d test', Proc. BMVC, 2002, Cardiff, UK, p. 448–457.
8. 8)
  - H. Wang , D. Suter . Robust adaptive-scale parametric model estimation for computer vision. IEEE Trans. Pattern Anal. Mach. Intell. , 11 , 1459 - 1474
9. 9)
  - D. Hasler , L. Sbaiz , S. Ssstrunk , M. Vetterli . Outlier modeling in image matching. IEEE Trans. Pattern Anal. Mach. Intell. , 3 , 301 - 315
10. 10)
  - R. Hartley . (2003) Multiple view geometry in computer vision.
11. 11)
  - Clarke, J., Carlsson, S., Zisserman, A.: `Detecting and tracking linear features efficiently', Proc. Seventh BMVC, 1996, p. 415–424.
12. 12)
  - M.A. Fischler , R.C. Bolles . Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM , 381 - 395
13. 13)
  - Xu, M., Petrou, M.: `Distributed ransac for 3D reconstruction', Proc. 20th Annual IST/SPIE Symp. Electronic Imaging, 2008, p. 6805w.
14. 14)
  - P. Torr , C. Davidson . IMPSAC: synthesis of importance sampling and random sample consensus. IEEE Trans. Pattern Anal. Mach. Intell. , 3 , 354 - 364
15. 15)
  - Schaffalitzky, F., Zisserman, A.: `Viewpoint invariant texture matching and wide baseline stereo', Proc. ICCV, 2001, Vancouver, BC, Canada, p. 636–643.
16. 16)
  - Matas, J., Chum, O.: `Randomized RANSAC with sequential probability ratio test', Proc. ICCV, 2005, Beijing, China, p. 1727–1732.
17. 17)
  - D. Nistr . Preemptive RANSAC for live structure and motion estimation. Mach. Vis. Appl. , 5 , 321 - 329
18. 18)
  - H. Kawakami , Y. Ito , Y. Kanazawa . A robust method for detecting planar regions based on random sampling using distributions of feature points. Syst. Comput. Jpn. , 4 , 11 - 22
19. 19)
  - IST06: ‘E-training for interpreting images of man-made scenes’. Available at http://www.ipb.uni-bonn.de/projects/etrims/.
20. 20)
  - X. Li , Y. Liu , Y. Wang , D. Yan . Computing homography with RANSAC algorithm: a novel method of registration. Proc. SPIE , 109 - 112
21. 21)
  - Cantzler, H., Fisher, R., Devy, M.: `Improving architectural 3D reconstruction by plane and edge constraining', Proc. BMVC, 2002, Cardiff, UK, p. 43–52.
22. 22)
  - Chum, O., Werner, T., Matas, J.: `Two-view geometry estimation unaffected by a dominant plane', Proc. CVPR’05, 2005, p. 772–779.

Distributed RANSAC for the robust estimation of three-dimensional reconstruction

Distributed RANSAC for the robust estimation of three-dimensional reconstruction

Buy article PDF

Buy Knowledge Pack

Thank you

References

Related content