Information Technology Reference
In-Depth Information
discussion seems to be quite open concerning many evolutions of the original
RANSAC algorithm [7], the impact of the presented rigidity constraint is objec-
tively undeniable and profitable for any mapping algorithm and any RANSAC
derivative.
Given that our first motivation was initially to prevent non rigid-body trans-
formations when estimating homographies, the substantial speed-up factor
achieved thanks to the proposed rigidity constraint is an unexpected, but very
positive result.
References
1. Fischler, M.A., Bolles, R.C.: Random sample consensus: A paradigm for model
fitting with applications to image analysis and automated cartography. Communi-
cations of the ACM 24, 381-395 (1981)
2. Faugeras, O.: Three-Dimensional Computer Vision: a Geometric Viewpoint. The
MIT Press, Cambridge (1993)
3. Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn.
Cambridge University Press, Cambridge (2003)
4. Simler, C., Monnin, D., Georges, V., Cudel, C.: A robust technique to establish
correspondences in case of important rotations around the optical axis. In: Advanced
Concepts for Intelligent Vision Systems, ACVIS 2004, Brussels, Belgium (2004)
5. Simler, C., Monnin, D., Cudel, C., Georges, V.: Robust automatic image mosaic gen-
eration. In: Proceedings of PSIP 2005, Fourth International Conference on Physics
in Signal Image Processing, Toulouse, France (2005)
6. Marquez-Neila, P., Miro, J.G., Buenaposada, J.M., Baumela, L.: Improving
RANSAC for fast landmark recognition. In: Computer Vision and Pattern Recog-
nition Workshops, pp. 1-8. IEEE Computer Society, Los Alamitos (2008)
7. Choi, S., Kim, T., Yu, W.: Performance evaluation of RANSAC family (2009)
Search WWH ::
Custom Search