Abstract
Efficient segmentation of color images is important for many applications in computer vision. Non-parametric solutions are required in situations where little or no prior knowledge about the data is available. In this paper, we present a novel parallel image segmentation algorithm which segments images in real-time in a non-parametric way. The algorithm finds the equilibrium states of a Potts model in the superparamagnetic phase of the system. Our method maps perfectly onto the Graphics Processing Unit (GPU) architecture and has been implemented using the framework NVIDIA Compute Unified Device Architecture (CUDA). For images of 256 ×320 pixels we obtained a frame rate of 30 Hz that demonstrates the applicability of the algorithm to video-processing tasks in real-time.
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
Shapiro, L.G., Stockman, G.C.: Computer Vision. Prentice-Hall, Englewood Cliffs (2001)
Sahoo, P.K., Soltani, S., Wong, A.K.C., Chen, Y.: A survey of thresholding techniques. Computer Vision, Graphics and Image Processing 41(2), 233–260 (1988)
Swendsen, R.H., Wang, S.: Nonuniversal critical dynamics in Monte Carlo simulations. Physical Review Letters 76(18), 86–88 (1987)
Wolff, U.: Collective Monte Carlo updating for spin systems. Physical Review Letters 62(4), 361–364 (1989)
von Ferber, C., Wörgötter, F.: Cluster update algorithm and recognition. Physical Review E 62(2), 1461–1464 (2000)
Boykov, Y., Funka-Lea, G.: Graph cuts and efficient N-D image segmentation. International Journal of Computer Vision 70(2), 109–131 (2006)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. International Journal of Computer Vision 59(2), 167–181 (2004)
Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. Pattern Analysis and Machine Intelligence 24(5), 603–619 (2002)
Potts, R.B.: Some generalized order-disorder transformations. Proc. Cambridge Philos. Soc. 48, 106–109 (1952)
Eckes, C., Vorbrüggen, J.C.: Combining data-driven and model-based cues for segmentation of video sequences. In: Proc. of World Congress on Neural Networks, pp. 868–875 (1996)
Blatt, M., Wiseman, S., Domany, E.: Superparamagnetic clustering of data. Physical Review Letters 76(18), 3251–3254 (1996)
Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minmization in vision. Pattern Analysis and Machine Intelligence 9, 1124–1137 (2004)
Ising, E.: Beitrag zur Theorie des Ferromagnetismus. Z. Phys. 31, 253–258 (1925)
Geman, D., Geman, S.: Stochastic relaxation, gibbs distributions, and the bayesian restoration of images. Pattern Analysis and Machine Intelligence 6, 721–741 (1984)
Meribout, M., Nakanishi, M.: A new real time object segmentation and tracking algorithm and its parallel architecture. Journal of VLSI Signal Processing 39(3), 249–266 (2005)
Carnevali, P., Coletti, L., Patarnello, S.: Image processing by simulated annealing. IBM Journal of Research and Development 29(6), 569–579 (1985)
Metropolis, N., Rosenbluth, A.W., Rosenbluth, M.N., Teller, A.H., Teller, E.: Equation of state calculations by fast computing machines. J. of Chem. Phys. 21(11), 1087–1091 (1953)
Barkema, G.T., MacFarland, T.: Parallel simulation of the ising model. Physical Review E 50(2), 1623–1628 (1994)
He, L., Chao, Y., Suzuki, K., Wu, K.: Fast connected-component labeling. Pattern Recognition 42, 1977–1987 (2009)
Kim, E., Wang, W., Li, H., Huang, X.: A parallel annealing method for automatic color cervigram image segmentation. In: Medical Image Computing and Computer Assisted Intervention, MICCAI-GRID 2009 HPC Workshop (2009)
Vineet, V., Narayanan, P.J.: CUDA cuts: fast graph cuts on the GPU. In: Proc. CVPRW 2008, pp. 1–8 (2008)
Dellen, B., Aksoy, E.E., Wörgötter, F.: Segment tracking via a spatiotemporal linking process including feedback stabilization in an n-d lattice model. Sensors 9(11), 9355–9379 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Abramov, A., Kulvicius, T., Wörgötter, F., Dellen, B. (2010). Real-Time Image Segmentation on a GPU. In: Keller, R., Kramer, D., Weiss, JP. (eds) Facing the Multicore-Challenge. Lecture Notes in Computer Science, vol 6310. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-16233-6_14
Download citation
DOI: https://doi.org/10.1007/978-3-642-16233-6_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-16232-9
Online ISBN: 978-3-642-16233-6
eBook Packages: Computer ScienceComputer Science (R0)