Abstract
In this paper, we propose a new stereo matching method using the population-based Markov Chain Monte Carlo (Pop-MCMC). Pop-MCMC belongs to the sampling-based methods. Since previous MCMC methods produce only one sample at a time, only local moves are available. However, since Pop-MCMC uses multiple chains and produces multiple samples at a time, it enables global moves by exchanging information between samples, and in turn leads to faster mixing rate. In the view of optimization, it means that we can reach a state with the lower energy. The experimental results on real stereo images demonstrate that the performance of proposed algorithm is superior to those of previous algorithms.
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
Scharstein, D., Szeliski, R.: A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms. Microsoft Research Technical Report MSR-TR-2001-81 (2001)
Birchfield, S., Tomasi, C.: A Pixel Dissimilarity Measure That is Insensitive to Image Sampling. IEEE Trans. Pattern Analysis and Machine Intelligence (1998)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Analysis and Machine Intelligence 23(11), 1222–1239 (2001)
Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions using graph cuts. In: Proc. Int’l. Conf. Computer Vision, pp. 508–515 (2001)
Kolmogorov, V., Zabih, R.: Multi-camera scene reconstruction via graph cuts. In: Proc. European Conf. Computer Vision, pp. 82–96 (2002)
Sun, J., Zheng, N.N., Shum, H.Y.: Stereo matching using belief propagation. IEEE Trans. Pattern Analysis and Machine Intelligence 25(7), 787–800 (2003)
Ohta, Y., Kanade, T.: Stereo by intra- and inter-scanline search. TPAMI 2, 449–470 (1985)
Veksler, O.: Stereo Correspondence by Dynamic Programming on a Tree. Computer Vision and Pattern Recognition (2005)
Barbu, A., Zhu, S.C.: Graph Partition By Swendsen-Wang cuts: International Conf. Computer Vision, pp. 320–327 (2003)
Barbu, A., Zhu, S.C.: Multigrid and multi-level Swendsen-Wang cuts for hierarchic graph partition. Computer Vision and Pattern Recognition, 731–738 (2004)
Kirkpatrick, S., Gelatt, C., Vecchi, M.: Optimization by simulated annealing. Science 220(4598), 671–680 (1983)
Liang, F., Wong, W.H.: Evolutionary Monte Carlo: Applications to Model Sampling and Change Point Problem. Statistica Sinica 10, 317–342 (2000)
Jasra, A., Stephens, D.A.: On Population-Based Simulation for Static Inference (2005)
Comanicu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Machine Intell. 24, 603–619 (2002)
Tao, H., Sawhney, H.S., Kumar, R.: A Global Matching Framework for Stereo Computation. In: Proc. Int’l. Conf. Computer Vision, vol. 1, pp. 532–539 (2001)
Bleyer, M., Gelautz, M.: Graph-based surface reconstruction from stereo pairs using image segmentation. In: Proc. SPIE, Videometrics VIII, vol. 5665, pp. 288–299 (2005)
Hong, L., Chen, G.: Segment-Based Stereo Matching Using Graph Cuts. Computer Vision and Pattern Recognition, I, 74–81 (2004)
Klaus, A., Sormann, M., Karner, K.: Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure. In: International Conf. Pattern Recognition, pp. 15–18 (2006)
Geyer, C.J.: Markov chain Monte Carlo maximum likelihood, Computing Science and Statistics, 156–163 (1991)
Hukushima, K., Nemoto, K.: Exchange Monte Carlo method and application to spin glass simulations. J. Phys. Soc. Jpn. 65, 1604–1608
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Park, J., Kim, W., Lee, K.M. (2007). Stereo Matching Using Population-Based MCMC. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds) Computer Vision – ACCV 2007. ACCV 2007. Lecture Notes in Computer Science, vol 4844. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76390-1_55
Download citation
DOI: https://doi.org/10.1007/978-3-540-76390-1_55
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76389-5
Online ISBN: 978-3-540-76390-1
eBook Packages: Computer ScienceComputer Science (R0)