Abstract
This communication addresses the problem of estimating the parameters of a family of marked point processes. These processes are of interest in extraction of object networks from remote sensing images. They are defined from a combination of several energy terms. First, a data energy term controls the localization of the objects with respect to the data. Second, prior information is given by intern energy terms corresponding to geometrical constraints on the configuration to be detected. An estimation procedure of the weight associated with these energies is studied. The application to unsupervised detection of objects is finally discussed.
This work was partially funded by CNES and by associated team ODESSA, and was conducted during a postdoc fellowship of the first author at INRIA Sophia Antipolis.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Descombes, X., Kruggel, F., Lacoste, C., Ortner, M., Perrin, G., Zerubia, J.: Marked point process in image analysis: from context to geometry. In: Int. Conference on Spatial Point Process Modelling and its Application (SPPA), Castellon, Spain (2004)
Lacoste, C., Descombes, X., Zerubia, J.: Point processes for unsupervised line network extraction in remote sensing. IEEE Trans. Pattern Analysis and Machine Intelligence 27(10), 1568–1579 (2005)
Ortner, M., Descombes, X., Zerubia, J.: A marked point process of rectangles and segments for automatic analysis of digital elevation models. IEEE Trans. Pattern Analysis and Machine Intelligence 30(1), 105–119 (2008)
Perrin, G., Descombes, X., Zerubia, J.: 2d and 3d vegetation resource parameters assessment using marked point processes. In: Proc. International Conference on Pattern Recognition (ICPR), Hong-Kong (August 2006)
Descamps, S., Descombes, X., Béchet, A., Zerubia, J.: Automatic flamingo detection using a multiple birth and death process. In: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008), pp. 304–306 (2008)
Geyer, C.: On the convergence of Monte Carlo maximum likelihood calculations. Journal of the Royal Statistical Society, Series B 56, 261–274 (1994)
Geyer, C.: Likelihood inference for spatial point process. In: Stochastic Geometry - Likelihood and Computation. Chapman and Hall/CRC (1999)
Descombes, X., van Lieshout, M., Stoica, R., Zerubia, J.: Parameter estimation by a Markov chain Monte Carlo technique for the Candy-model. In: Proc. of IEEE Workshop on Statistical Signal Processing, Singapour (August 2001)
Jensen, J., Møller, J.: Pseudolikelihood for exponential family models of spatial point processes. The Annals of Applied Probability 1(3), 445–461 (1991)
Jensen, J., Kunsch, R.: On asymptotic normality of pseudo likelihood estimates for pairwise interaction processes. Ann. Inst. Statist. Math. 46, 475–486 (1994)
Mase, S.: Consistency of the maximum pseudo-likelihood estimator of continuous state space Gibbsian processes. The Annals of Applied Probability 5(3), 603–612 (1995)
Mateu, J., Montes, F.: Pseudo-likelihood inference for Gibbs processes with exponential families through generalized linear models. Statistical Inference for Stochastic Processes 4(2), 125–154 (2001)
Baddeley, A., Turner, R.: Practical maximum pseudolikelihood for spatial point patterns (with discussion). Australian and New Zealand Journal of Statistics 42(3), 283–322 (2000)
Billiot, J.M., Coeurjolly, J.F., Drouilhet, R.: Maximum pseudo-likelihood estimator for nearest-neighbours Gibbs point processes. Electronic Journal of Statistics 2, 234–264 (2008)
Van Lieshout, M.N.M.: Markov Point Processes and Their Applications. Imperial College Press, London (2000)
Perrin, G., Descombes, X., Zerubia, J.: A non-Bayesian model for tree crown extraction using marked point processes. Research Report 5846, INRIA, France (February 2006)
Welch, B.L.: The generalization of Student’s problem when several different population variances are involved. Biometrika 34, 28–35 (1947)
Green, P.: Reversible jump Markov chain Monte Carlo computation and Bayesian model determination. Biometrika 82, 711–732 (1995)
Perrin, G., Descombes, X., Zerubia, J.: Adaptive simulated annealing for energy minimization problem in a marked point process application. In: Proc. Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), St Augustine, Florida, USA (November 2005)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Stat. Society. Series B (Methodological) 39(1), 1–38 (1977)
Celeux, G., Chauveau, D., Diebolt, J.: On stochastic versions of the EM algorithm. Research Report 2514, INRIA (March 1995)
Besag, J.: Some methods of statistical analysis for spatial data. Bulletin of the International Statistical Institute 47, 77–92 (1977)
Besag, J., Milne, R., Zachary, S.: Point process limits of lattice processes. Journal of Applied Probability 19, 210–216 (1982)
Møller, J., Waagepetersen, R.: Statistical inference and simulation for spatial point processes. Chapman and Hall/CRC, Boca Raton (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chatelain, F., Descombes, X., Zerubia, J. (2009). Parameter Estimation for Marked Point Processes. Application to Object Extraction from Remote Sensing Images. In: Cremers, D., Boykov, Y., Blake, A., Schmidt, F.R. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2009. Lecture Notes in Computer Science, vol 5681. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03641-5_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-03641-5_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03640-8
Online ISBN: 978-3-642-03641-5
eBook Packages: Computer ScienceComputer Science (R0)