Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Motion of moving camera from point matches: comparison of two robust estimation methods

A robust estimation method, Balanced Least Absolute Value Estimator (BLAVE), is introduced and compared with the traditional RANdom SAmple Consensus (RANSAC) method. The comparison is performed empirically by applying both estimators on the camera motion parameters estimation problem. A linearised model for this estimation problem is derived. The tests were performed on a simulated scene with added random noise and gross errors as well as on actual images taken by a mobile mapping system. The greatest advantage of BLAVE is that it processes all observations at once as well as its median-like property: the estimated parameters are not influenced by the size of the outliers. It can tolerate up to 50% outliers in data and still produce accurate results. The greatest disadvantage of RANSAC is that the results are not repeatable because of the random sampling of data. Moreover, the results are less accurate, because RANSAC generally does not produce a ‘best-fit’ parameter estimation. The number of trials, which must be tested by RANSAC to find a reasonable solution, depends on the portion of outliers in data. The computational time for BLAVE does not depend on the portion of outliers in the observations, but it grows with the number of observations, same as RANSAC.

References

    1. 1)
      • 6. Sonka, M., Hlavac, V., Boyle, R.: ‘Image processing, analysis, and machine vision’ (Thomson Learning, 2007), pp. 175249.
    2. 2)
    3. 3)
      • 15. Coleman, T.F., Li, Y.: ‘A Global and quadratic affine scaling method for linear L1 problems’ (Cornell University, TR 89-1026, 1989).
    4. 4)
    5. 5)
      • 20. Choi, S., Kim, T., Yu, W.: ‘Performance evaluation of RANSAC family’. Proc. 2009 British Machine Vision Conf., 2009, pp. 112.
    6. 6)
      • 3. Harris, C.G.: ‘Determination of ego-motion from matched points’. Proc. 3rd Alvey Vision Conf., 1987, pp. 189192.
    7. 7)
      • 14. Jurisch, R., Kampmann, G., Linke, J.: ‘Introducing the determination of hidden (latent) restrictions within linear regression analysis’, in Grafarend, E., Krumm, F.W., Schwarze, V.S. (Eds.): ‘Geodesy – the challenge of the 3rd millenium’ (Springer, Berlin, Germany, 2002), pp. 333348.
    8. 8)
    9. 9)
      • 12. Jurisch, R., Kampmann, G.: ‘Pluecker coordinates: a new tool for geometrical analysis and outlier detection’. First Int. Symp. on Robust Statitics and Fuzzy Techniques in Geodesy and GIS, 2001, pp. 95109.
    10. 10)
      • 21. Leick, A.: ‘GPS satellite surveying’ (Wiley, 2004, 3rd edn.).
    11. 11)
      • 18. Fisher, R.B.: ‘The RANSAC (Random Sample Consensus) Algorithm’. Informatics homepage: http://homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_COPIES/FISHER/RANSAC/, Accessed December 2012.
    12. 12)
      • 13. Grafarend, E.W., Awange, J.L.: ‘Applications of linear and nonlinear models- fixed effects, random effects, and total least squares’ (Springer, 2012), pp. 142.
    13. 13)
      • 19. Zuliani, M.: ‘RANSAC for Dummies’. http://vision.ece.ucsb.edu/~zuliani/Research/RANSAC/docs/RANSAC4Dummies.pdf, Accessed December 2012.
    14. 14)
      • 23. The KITTI Vision Benchmark Suite http://www.cvlibs.net/datasets/kitti/raw_data.php, Accessed January 2014.
    15. 15)
      • 5. Gonzalez, R.C., Woods, R.E.: ‘Digital image processing using MATLAB’ (Prentice-Hall, 2002, 2nd edn.), pp. 567634.
    16. 16)
    17. 17)
    18. 18)
      • 7. Lowe, D.G.: ‘Object recognition from local scale-invariant features’. Proc. Int. Conf. on Computer Vision 2, 1999, pp. 11501157.
    19. 19)
      • 8. Wilcox, R.R.: ‘Introduction to robust estimation and hypothesis testing’ (Academic Press, 2012, 3rd edn.), pp. 489498.
    20. 20)
      • 4. Hartley, R., Zisserman, A.: ‘Multiple view geometry in computer vision’ (Cambridge University Press, 2004, 2nd edn.), pp. 257259.
    21. 21)
      • 24. Harris, C., Stephens, M.: ‘A combined corner and edge detector’. Proc. 4th Alvey Vision Conf., 1988, pp. 147151.
    22. 22)
      • 10. Jurisch, R., Kampmann, G.: ‘Vermittelnde Ausgleichungsrechnung mit balancierten Beobachtungen – erste Schritte zu einem neuen Ansatz’, Z.Vermess.wes., 1998, 123, pp. 8792.
    23. 23)
    24. 24)
      • 11. Kampmann, G., Renner, B.: ‘Numerische beispiele zur bearbeitung latenter bedingungen und zur interpretation von mehrfachbeobachtungen in der ausgleichungsrechnung’, Z. Vermess.wes., 2000, 125, pp. 190197.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2013.0271
Loading

Related content

content/journals/10.1049/iet-cvi.2013.0271
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address