International Journal of Computer Vision

, Volume 106, Issue 1, pp 57–75 | Cite as

Detecting parametric objects in large scenes by Monte Carlo sampling

Article

Abstract

Point processes constitute a natural extension of Markov random fields (MRF), designed to handle parametric objects. They have shown efficiency and competitiveness for tackling object extraction problems in vision. Simulating these stochastic models is however a difficult task. The performances of the existing samplers are limited in terms of computation time and convergence stability, especially on large scenes. We propose a new sampling procedure based on a Monte Carlo formalism. Our algorithm exploits the Markovian property of point processes to perform the sampling in parallel. This procedure is embedded into a data-driven mechanism so that the points are distributed in the scene in function of spatial information extracted from the input data. The performances of the sampler are analyzed through a set of experiments on various object detection problems from large scenes, including comparisons to the existing algorithms. The sampler is also tested as optimization algorithm for MRF-based labeling problems.

Keywords

Stochastic modeling Monte Carlo sampling Object detection Large scenes Energy minimization Point processes Markov random fields 

Notes

Acknowledgments

This work was partially funded by the European Research Council (ERC Starting Grant “Robust Geometry Processing”, Grant agreement 257474). The authors thank A. Lehmussola, V. Lempitsky, H. Bischof, R. Ehrich, the French Mapping Agency (IGN), the Tour du Valat, and the BRGM for providing the datasets, as well as the reviewers for their valuable comments.

References

  1. Baddeley, A. J., & Lieshout, M. V. (1993). Stochastic geometry models in high-level vision. Journal of Applied Statistics, 20(5–6), 231–256.CrossRefGoogle Scholar
  2. Benchmark, (2013). Datasets, results and evaluation tools. http://www-sop.inria.fr/members/Florent.Lafarge/benchmark/evaluation.html.
  3. Besag, J. E. (1986). On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society, 48(3), 259–302.MATHMathSciNetGoogle Scholar
  4. Boykov, Y., Veksler, O., & Zabih, R. (2001). Fast approximate energy minimization via graph cuts. Pattern Analysis and Machine Intelligence, 23(11), 1222–1239.CrossRefGoogle Scholar
  5. Byrd, J., Jarvis, S., & Bhalerao, A. (2010). On the parallelisation of mcmc-based image processing. IEEE International Symposium on Parallel and Distributed Processing. Atlanta, US.Google Scholar
  6. Chai, D., Forstner, W., & Lafarge, F. (2013). Recovering line-networks in images by junction-point processes. Computer Vision and Pattern Recognition, Portland.Google Scholar
  7. Chai, D., Forstner, W., & Yang, M. Y. (2012). Combine Markov random fields and marked point processes to extract building from remotely sensed images. International Society for Photogrammetry and Remote Sensing Congress. Melbourne, Australia.Google Scholar
  8. Descombes, X. (2011). Stochastic geometry for image analysis. Oxford: Wiley.Google Scholar
  9. Descombes, X., Minlos, R., & Zhizhina, E. (2009). Object extraction using a stochastic birth-and-death dynamics in continuum. Journal of Mathematical Imaging and Vision, 33(3), 347–359.CrossRefMathSciNetGoogle Scholar
  10. Earl, D., & Deem, M. (2005). Parallel tempering: Theory, applications, and new perspectives. Physical Chemistry Chemical Physics, 23(7), 3910–3916.CrossRefGoogle Scholar
  11. Ge, W., & Collins, R. (2009). Marked point processes for crowd counting. Computer Vision and Pattern Recognition. Miami. Google Scholar
  12. Gonzalez, J., Low, Y., Gretton, A., & Guestrin, C. (2011). Parallel Gibbs sampling: From colored fields to thin junction trees. Journal of Machine Learning Research, 15, 324–332.Google Scholar
  13. Green, P. (1995). Reversible jump Markov chains Monte Carlo computation and Bayesian model determination. Biometrika, 82(4), 711–732.CrossRefMATHMathSciNetGoogle Scholar
  14. Grenander, U., & Miller, M. (1994). Representations of knowledge in complex systems. Journal of the Royal Statistical Society, 56(4), 549–603.MATHMathSciNetGoogle Scholar
  15. Han, F., Tu, Z. W., & Zhu, S. (2004). Range image segmentation by an effective jump-diffusion method. Pattern Analysis and Machine Intelligence, 26(9), 1138–1153.CrossRefGoogle Scholar
  16. Harkness, M., & Green, P. (2000). Parallel chains, delayed rejection and reversible jump mcmc for object recognition. British Machine Vision Conference. Bristol, United Kingdom.Google Scholar
  17. Hastings, W. (1970). Monte Carlo sampling using Markov chains and their applications. Biometrika, 57(1), 97–109.CrossRefMATHGoogle Scholar
  18. Lacoste, C., Descombe, X., & Zerubia, J. (2005). Point processes for unsupervised line network extraction in remote sensing. Pattern Analysis and Machine Intelligence, 27(10), 1568–1579.CrossRefGoogle Scholar
  19. Lafarge, F., Gimel’farb, G., & Descombes, X. (2010). Geometric feature extraction by a multi-marked point process. Pattern Analysis and Machine Intelligence, 32(9), 1597–1609.CrossRefGoogle Scholar
  20. Lafarge, F., & Mallet, C. (2012). Creating large-scale city models from 3d-point clouds: A robust approach with hybrid representation. International Journal of Computer Vision, 99(1), 69–85.CrossRefMathSciNetGoogle Scholar
  21. Lehmussola, A., Ruusuvuori, P., Selinummi, J., Huttunen, H., & Yli-Harja, O. (2007). Computational framework for simulating fluorescence microscope images with cell populations. IEEE Transactions on Medical Imaging, 26(7), 1010–1016.Google Scholar
  22. Lempitsky, V., & Zisserman, A. (2010). Learning to count objects in images. Conference on Neural Information Processing Systems. Vancouver, Canada.Google Scholar
  23. Li, S. (2001). Markov random field modeling in image analysis. Berlin: Springer.CrossRefMATHGoogle Scholar
  24. Lieshout, M. V. (2008). Depth map calculation for a variable number of moving objects using markov sequential object processes. Pattern Analysis and Machine Intelligence, 30(7), 1308–1312.CrossRefGoogle Scholar
  25. Liu, J. (2001). Monte Carlo strategies in scientific computing. New York: Springer.MATHGoogle Scholar
  26. Mallet, C., Lafarge, F., Roux, M., Soergel, U., Bretar, F., & Heipke, C. (2010). A marked point process for modeling lidar waveforms. IEEE Transactions on Image Processing, 19(12), 3204–3221.CrossRefMathSciNetGoogle Scholar
  27. Nguyen, H.-G., Fablet, R., & Bouchet, J. (2010). Spatial statistics of visual keypoints for texture recognition. European Conference on Computer Vision. Heraklion, Greece.Google Scholar
  28. Ortner, M., Descombes, X., & Zerubia, J. (2008). A marked point process of rectangles and segments for automatic analysis of digital elevation models. Pattern Analysis and Machine Intelligence, 30(1), 105–119.CrossRefGoogle Scholar
  29. Rochery, M., Jermyn, I., & Zerubia, J. (2006). Higher order active contours. International Journal of Computer Vision, 69(3), 335–351.CrossRefGoogle Scholar
  30. Salamon, P., Sibani, P., & Frost, R. (2002). Facts, Conjectures, and Improvements for Simulated Annealing. Philadelphia: SIAM Monographs on Mathematical Modeling and Computation.Google Scholar
  31. Srivastava, A., Grenander, U., Jensen, G., & Miller, M. (2002). Jump-Diffusion Markov processes on orthogonal groups for object pose estimation. Journal of Statistical Planning and Inference, 103(1–2), 15–27.CrossRefMATHMathSciNetGoogle Scholar
  32. Stoica, R. S., Martinez, V., & Saar, E. (2007). A three dimensional object point process for detection of cosmic filaments. Journal of the Royal Statistical Society, 56(4), 459.Google Scholar
  33. Sun, K., Sang, N., & Zhang, T. (2007). Marked point process for vasculartree extraction on angiogram. Energy Minimization Methods in Computer Vision and Pattern Recognition. Ezhou, China.Google Scholar
  34. Szeliski, R., Zabih, R., Scharstein, D., Veksler, O., Kolmogorov, V., Agarwala, A., et al. (2008). Comparative study of energy minimization methods for markov random fields with smoothness-based priors. Pattern Analysis and Machine Intelligence, 30(6), 1068.CrossRefGoogle Scholar
  35. Tu, Z., & Zhu, S. (2002). Image segmentation by data-driven Markov chain Monte Carlo. Pattern Analysis and Machine Intelligence, 24(5), 657–673.CrossRefGoogle Scholar
  36. Utasi, A., & Benedek, C. (2011). A 3-D marked point process model for multi-view people detection. Conference on Computer Vision and Pattern Recognition. Colorado Springs, US. Google Scholar
  37. Verdie, Y., & Lafarge, F. (2012). Efficient Monte Carlo sampler for detecting parametric objects in large scenes. European Conference on Computer Vision. Firenze, Italy.Google Scholar
  38. Weiss, Y., & Freeman, W. (2001). On the optimality of solutions of the max-product belief propagation algorithm in arbitrary graphs. IEEE Transactions on Information Theory, 47(2), 736–744.CrossRefMATHMathSciNetGoogle Scholar
  39. Zhu, S., Guo, C., Wang, Y., & Xu, Z. (2005). What are textons? International Journal of Computer Vision, 62(1–2), 121–143.Google Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.INRIASophia AntipolisFrance

Personalised recommendations