Abstract
In the present paper, we propose a method for reconstructing the shapes of block-like objects from stereovision data. Flat surfaces and ridge lines are represented by three-dimensional (3-D) discrete object models. Interrelations between the object models are formulated by use of the framework of a 3-D Markov Random Field (MRF) model. The shape reconstruction is accomplished by searching for the most likely state of the MRF model. The searching is performed by the Markov Chain Monte Carlo (MCMC) method. An experimental result is shown for real stereo data.
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
Grimson, W.: From Images to Surfaces, A Computational Study of the Human Early Visual System. MIT Press, Cambridge (1981)
Floriani, L., Puppo, E.: Constrained Delaunay Triangulation for Multiresolution Surface Description. In: Proc. International Conference on Pattern Recognition 1988, pp. 566–569 (1988)
Faugeras, O.D., Bras-Mehlman, E., Boissonnat, J.D.: Representing Stereo Data with the Delaunay Triangulation. Artificial Intelligence 44, 41–87 (1990)
Taylor, C.J.: Surface Reconstruction from Feature Based Stereo. In: Proceedings of the 9th IEEE International Conference on Computer Vision, pp. 184–190 (2003)
Geman, S., Geman, D.: Stochastic Relaxation, Gibbs Distribution, and the Bayesian Restoration of Images. IEEE Trans. on Pattern Analysis and Machine Intelligence(PAMI) PAMI-6(6), 721–742 (1984)
Takizawa, H., Yamamoto, S.: Surface Reconstruction from Stereo Data using a Three-dimensional Markov Random Field Model. IEICE Transactions on Information and Systems E89-D(7), 2028–2035 (2006)
Winkler, G.: Image Analysis, Random Fields and Markov Chain Monte Carlo Methods. Springer, Heidelberg (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Takizawa, H. (2008). 3-D Shape Reconstruction from Stereovision Data Using Object-Consisted Markov Random Field Model. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds) Neural Information Processing. ICONIP 2007. Lecture Notes in Computer Science, vol 4985. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69162-4_64
Download citation
DOI: https://doi.org/10.1007/978-3-540-69162-4_64
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69159-4
Online ISBN: 978-3-540-69162-4
eBook Packages: Computer ScienceComputer Science (R0)