Marked point process in image analysis

IEEE Signal Processing Magazine - Tập 19 Số 5 - Trang 77-84 - 2002
X. Descombes, J. Zerubia1
1INRIA

Tóm tắt

In this article, we consider the marked point process framework for image analysis. We first show that marked point processes are more adapted than Markov random fields (MRFs) including some geometrical constraints in the solution and dealing with strongly correlated noise. Then, we consider three applications in remote sensing: road network extraction, building extraction, and image segmentation. For each of them, we define a prior model, incorporating geometrical constraints on the solution. We also derive a reversible jump Monte Carlo Markov chains (RJMCMC) algorithm to obtain the optimal solution with respect to the defined models. Results show that this approach is promising and can be applied to a broad range of image processing problems.

Từ khóa

#Image analysis #Image segmentation #Bayesian methods #Remote sensing #Lattices #Cascading style sheets #Markov random fields #Roads #Solid modeling #Monte Carlo methods

Tài liệu tham khảo

waagepetersen, 1997, Contributions to the statistical modelling of image data and spatial point patterns 10.1109/36.662728 10.1093/biomet/82.4.711 green, 1996, mcmc in image analysis, Markov Chain Monte Carlo in Practice, 381 grenander, 1993, General Pattern Theory grenander, 1994, representations of knowledge in complex systems, J Royal Stat Soc, 56, 549 10.1006/cviu.1998.0731 10.1111/1467-9876.00115 imberty, 2000, Simulation de processus objets Etude de faisabilit&#x00E9 pour une application &#x00E1 la segmentation d image 10.1117/12.213096 10.1006/cviu.1999.0750 10.1109/34.491623 10.1007/BF00535104 stoyan, 1987, Stochastic Geometry and its Applications besag, 1974, spatial interaction and the statistical analysis of lattice systems (with discussion), J Royal Statist Soc, 36, 192 10.1063/1.1381915 10.1109/SSP.2001.955212 10.1002/(SICI)1097-0258(19990915/30)18:17/18<2507::AID-SIM272>3.0.CO;2-J 10.1515/mcma.2001.7.1-2.149 10.1109/TPAMI.1984.4767596 garcin, 2001, buiding extraction using a markov point process, Proc ICIP 01 10.1080/02664769300000065 geyer, 1994, simulation and likelihood inference for spatial point process, Scand J Stat, 21, 359 10.1007/978-3-642-48678-4_34 10.1109/78.482117 ripley, 1997, modelling spatial patterns, J Royal Statistical Institute, 39, 172 ortner, 2001, Extraction de caricatures de batiments sur des mod&#x00E8 les num&#x00E9 riques d &#x00E9 l&#x00E9 vation robert, 1999, Monte Carlo Statistical Methods, 10.1007/978-1-4757-3071-5 10.1112/jlms/s2-15.1.188 10.1093/biomet/86.3.649 10.1239/aap/1035227992