Abstract
The averaging of multiple pairwise relative motions in a sequence provides a fast and accurate method of camera motion estimation with a wide range of applications, including view registration, robotic path estimation, super-resolution. Since this approach involves averaging in the Lie-algebra of the underlying motion representation, it is non-robust and susceptible to contamination due to outliers in the individual relative motions. In this paper, we introduce a graph-based sampling scheme that efficiently remove such motion outliers. The resulting global motion solution is robust and also provides an empirical estimate of the inherent statistical uncertainty. Example results are provided to demonstrate the efficacy of our approach to incorporating robustness in motion averaging.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)
Govindu, V.M.: Combining two-view constraints for motion estimation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 218–225 (2001)
Govindu, V.M.: Lie-algebraic averaging for globally consistent motion estimation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 684–691 (2004)
Fischler, M., Bolles, R.: Random sample consensus: a paradigm for model fitting with application to image analysis and automated cartography. Communications of the ACM 24, 381–395 (1981)
Torr, P.H.S., Murray, D.W.: The development and comparison of robust methods for estimating the fundamental matrix. International Journal of Computer Vision 24, 271–300 (1997)
Efron, B., Tibshirani, R.J.: An Introduction to the Bootstrap. Chapman and Hall, Boca Raton (1993)
Varadarajan, V.S.: Lie Groups, Lie Algebras and Their Representations. Graduate Texts in Mathematics, vol. 102. Springer, Heidelberg (1984)
Fletcher, P.T., Lu, C., Joshi, S.: Statistics of shape via principal component analysis on lie groups. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 95–101 (2003)
Georgescu, B., Meer, P.: Balanced recovery of 3d structure and camera motion from uncalibrated image sequences. In: European Conference on Computer Vision, pp. 294–308 (2002)
Levi, N., Werman, M.: The viewing graph. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 599–606 (2003)
Cormen, T., Leiserson, C., Rivest, R., Stein, C.: Introduction to Algorithms. MIT Press, Cambridge (2001)
Karger, D., Klein, P., Tarjan, R.: A randomized linear-time algorithm for finding minimum spanning trees. Journal of the ACM 42, 321–328 (1995)
Hartley, R.: In defence of the 8-point algorithm. In: Proceedings of the 5th International Conference on Computer Vision, pp. 1064–1070 (1995)
Mendonca, P.R.S., Cipolla, R.: A simple technique for self-calibration. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 112–116 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Govindu, V.M. (2006). Robustness in Motion Averaging. In: Narayanan, P.J., Nayar, S.K., Shum, HY. (eds) Computer Vision – ACCV 2006. ACCV 2006. Lecture Notes in Computer Science, vol 3852. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11612704_46
Download citation
DOI: https://doi.org/10.1007/11612704_46
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-31244-4
Online ISBN: 978-3-540-32432-4
eBook Packages: Computer ScienceComputer Science (R0)