Abstract
Point processes have demonstrated efficiency and competitiveness when addressing object recognition problems in vision. However, simulating these mathematical models is a difficult task, especially on large scenes. Existing samplers suffer from average performances in terms of computation time and stability. We propose a new sampling procedure based on a Monte Carlo formalism. Our algorithm exploits Markovian properties of point processes to perform the sampling in parallel. This procedure is embedded into a data-driven mechanism such that the points are non-uniformly distributed in the scene. The performances of the sampler are analyzed through a set of experiments on various object recognition problems from large scenes, and through comparisons to the existing algorithms.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Baddeley, A.J., Lieshout, M.V.: Stochastic geometry models in high-level vision. Journal of Applied Statistics 20 (1993)
Descombes, X., Minlos, R., Zhizhina, E.: Object extraction using a stochastic birth-and-death dynamics in continuum. JMIV 33 (2009)
Ge, W., Collins, R.: Marked point processes for crowd counting. In: CVPR, Miami, U.S. (2009)
Lafarge, F., Gimel’farb, G., Descombes, X.: Geometric feature extraction by a multi-marked point process. PAMI 32 (2010)
Lieshout, M.V.: Depth map calculation for a variable number of moving objects using markov sequential object processes. PAMI 30 (2008)
Mallet, C., Lafarge, F., Roux, M., Soergel, U., Bretar, F., Heipke, C.: A marked point process for modeling lidar waveforms. IP 19 (2010)
Lacoste, C., Descombe, X., Zerubia, J.: Point processes for unsupervised line network extraction in remote sensing. PAMI 27 (2005)
Sun, K., Sang, N., Zhang, T.: Marked Point Process for Vascular Tree Extraction on Angiogram. In: Yuille, A.L., Zhu, S.-C., Cremers, D., Wang, Y. (eds.) EMMCVPR 2007. LNCS, vol. 4679, pp. 467–478. Springer, Heidelberg (2007)
Utasi, A., Benedek, C.: A 3-D marked point process model for multi-view people detection. In: CVPR, Colorado Springs, U.S. (2011)
Green, P.: Reversible Jump Markov Chains Monte Carlo computation and Bayesian model determination. Biometrika 82 (1995)
Hastings, W.: Monte Carlo sampling using Markov chains and their applications. Biometrika 57 (1970)
Han, F., Tu, Z.W., Zhu, S.: Range image segmentation by an effective jump-diffusion method. PAMI 26 (2004)
Srivastava, A., Grenander, U., Jensen, G., Miller, M.: Jump-Diffusion Markov processes on orthogonal groups for object pose estimation. Journal of Statistical Planning and Inference 103 (2002)
Tu, Z., Zhu, S.: Image Segmentation by Data-Driven Markov Chain Monte Carlo. PAMI 24 (2002)
Harkness, M., Green, P.: Parallel chains, delayed rejection and reversible jump mcmc for object recognition. In: BMVC, Bristol, U.K (2000)
Byrd, J., Jarvis, S., Bhalerao, A.: On the parallelisation of mcmc-based image processing. In: IEEE International Symposium on Parallel and Distributed Processing, Atlanta, U.S. (2010)
Gonzalez, J., Low, Y., Gretton, A., Guestrin, C.: Parallel Gibbs sampling: From colored fields to thin junction trees. Journal of Machine Learning Research (2011)
Verdié, Y., Lafarge, F.: Towards the parallelization of Reversible Jump Markov Chain Monte Carlo algorithms for vision problems. Research report 8016, INRIA (2012)
Rochery, M., Jermyn, I., Zerubia, J.: Higher order active contours. IJCV 69 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Verdié, Y., Lafarge, F. (2012). Efficient Monte Carlo Sampler for Detecting Parametric Objects in Large Scenes. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7574. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33712-3_39
Download citation
DOI: https://doi.org/10.1007/978-3-642-33712-3_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33711-6
Online ISBN: 978-3-642-33712-3
eBook Packages: Computer ScienceComputer Science (R0)