Abstract
This contribution shows how unsupervised Markovian segmentation techniques can be accelerated when implemented on graphics hardware equipped with a Graphics Processing Unit (GPU). Our strategy exploits the intrinsic properties of local interactions between sites of a Markov Random Field model with the parallel computation ability of a GPU. This paper explains how classical iterative site-wise-update algorithms commonly used to optimize global Markovian cost functions can be efficiently implemented in parallel by fragment shaders driven by a fragment processor. This parallel programming strategy significantly accelerates optimization algorithms such as ICM and simulated annealing. Good acceleration are also achieved for parameter estimation procedures such as K-means and ICE. The experiments reported in this paper have been obtained with a mid-end, affordable graphics card available on the market.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Lucchese, L., Mitra, S.: Color Image Segmentation: A State-of-the-Art Survey. In: Proc. of INSA-A (2003)
Geman, S., Geman, D.: Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images. J. IEEE Trans. Pattern Anal. Machine Intell. 6(6), 721–741 (1984)
Besag, J.: On the Statistical Analysis of Dirty Pictures. J. Roy. Stat. Soc. 48(3), 259–302 (1986)
Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1996) ISBN:0-19-853849-9
Pieczynski, W.: Statistical Image Segmentation. J. Machine Graphics and Vision (1), 261–268 (1992)
Kirkpatrick, S., Gelatt, C., Vecchi, M.: Optimization by Simulated Annealing. J. Science 220(4598), 671–680 (1983)
Chou, P., Brown, C.: The Theory and Practice of Bayesian Image labeling. In: Proc. of ICCV, pp. 185–210 (1990)
Kruger, J., Westermann, R.: Linear algebra operators for GPU implementation of numerical algorithms. J. ACM Trans. Graph. 22(3), 908–916 (2003)
Moreland, K., Angel, E.: The FFT on a GPU. In: Proc. of Workshop on Graphics Hardware, pp. 112–119 (2003)
Dumontier, C., Luthon, F., Charras, J.-P.: Real-Time DSP Implementation for MFR-Based Video Motion Detection. J. IEEE Trans. on Img. Proc. 8(10), 1341–1347 (1999)
Murray, D., Kashko, A., Buxton, H.: A Parallel Approach to the Picture Restoration Algorithm of Geman and Geman on a SIMD Machine. J. Image and Vision Computing 4, 141–152 (1986)
Rost, R.: OpenGL Shading Language, 1st edn. Addison-Wesley, Reading (2004)
Akenine-Moller, T., Haines, E.: Real-time Rendering, 2nd edn. AK Peters (2002)
Fernando, R., Kilgard, M.: The Cg Tutorial: The Definitive Guide to Programmable Real-Time Graphics. Addison-Wesley, Reading (2003)
Barron, J., Fleet, D., Beauchemin, S.: Performance of optical flow techniques. J. Int. J. Comput. Vis. 12(1), 43–77 (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jodoin, PM., St-Amour, JF., Mignotte, M. (2005). Unsupervised Markovian Segmentation on Graphics Hardware. In: Singh, S., Singh, M., Apte, C., Perner, P. (eds) Pattern Recognition and Image Analysis. ICAPR 2005. Lecture Notes in Computer Science, vol 3687. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11552499_50
Download citation
DOI: https://doi.org/10.1007/11552499_50
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28833-6
Online ISBN: 978-3-540-31999-3
eBook Packages: Computer ScienceComputer Science (R0)