|
|
Publications about Marked point process
Result of the query in the list of publications :
5 Articles |
1 - Building Development Monitoring in Multitemporal Remotely Sensed Image Pairs with Stochastic Birth-Death Dynamics.
C. Benedek and X. Descombes and J. Zerubia. IEEE Trans. Pattern Analysis and Machine Intelligence, 34(1): pages 33-50, January 2012.
Keywords : Building extraction, Change detection, Marked point process, multiple birth-and-death dynamics.
Copyright : IEEE
@ARTICLE{benedekPAMI11,
|
| author |
= |
{Benedek, C. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Building Development Monitoring in Multitemporal Remotely Sensed Image Pairs with Stochastic Birth-Death Dynamics}, |
| year |
= |
{2012}, |
| month |
= |
{January}, |
| journal |
= |
{IEEE Trans. Pattern Analysis and Machine Intelligence}, |
| volume |
= |
{34}, |
| number |
= |
{1}, |
| pages |
= |
{33-50}, |
| url |
= |
{http://dx.doi.org/10.1109/TPAMI.2011.94}, |
| keyword |
= |
{Building extraction, Change detection, Marked point process, multiple birth-and-death dynamics} |
| } |
Abstract :
In this paper we introduce a new probabilistic method which integrates building extraction with change detection in remotely sensed image pairs. A global optimization process attempts to find the optimal configuration of buildings, considering the observed data, prior knowledge, and interactions between the neighboring building parts. We present methodological contributions in three key issues: (1) We implement a novel object-change modeling approach based on Multitemporal Marked Point Processes, which simultaneously exploits low level change information between the time layers and object level building description to recognize and separate changed and unaltered buildings. (2) To answering the challenges of data heterogeneity in aerial and satellite image repositories, we construct a flexible hierarchical framework which can create various building appearance models from different elementary feature based modules. (3) To simultaneously ensure the convergence, optimality and computation complexity constraints raised by the increased data quantity, we adopt the quick Multiple Birth and Death optimization technique for change detection purposes, and propose a novel non-uniform stochastic object birth process, which generates relevant objects with higher probability based on low-level image features. |
|
2 - A Marked Point Process Model Including Strong Prior Shape Information Applied to Multiple Object Extraction From Images.
M. S. Kulikova and I. H. Jermyn and X. Descombes and E. Zhizhina and J. Zerubia. International Journal of Computer Vision and Image Processing, 1(2): pages 1-12, 2011.
Keywords : Active contour, Marked point process, multiple birth-and-death dynamics, multiple object extraction, Shape prior.
@ARTICLE{kulikova_ijcvip2010,
|
| author |
= |
{Kulikova, M. S. and Jermyn, I. H. and Descombes, X. and Zhizhina, E. and Zerubia, J.}, |
| title |
= |
{A Marked Point Process Model Including Strong Prior Shape Information Applied to Multiple Object Extraction From Images}, |
| year |
= |
{2011}, |
| journal |
= |
{International Journal of Computer Vision and Image Processing}, |
| volume |
= |
{1}, |
| number |
= |
{2}, |
| pages |
= |
{1-12}, |
| url |
= |
{http://hal.archives-ouvertes.fr/hal-00804118}, |
| keyword |
= |
{Active contour, Marked point process, multiple birth-and-death dynamics, multiple object extraction, Shape prior} |
| } |
Abstract :
Object extraction from images is one of the most important tasks in remote sensing image analysis. For accurate extraction from very high resolution (VHR) images, object geometry needs to be taken into account. A method for incorporating strong yet flexible prior shape information into a marked point process model for the extraction of multiple objects of complex shape is presented. To control the computational complexity, the objects considered are defined using the image data and the prior shape information. To estimate the optimal configuration of objects, the process is sampled using a Markov chain based on a stochastic birth-and-death process on the space of multiple objects. The authors present several experimental results on the extraction of tree crowns from VHR aerial images. |
|
3 - Unsupervised line network extraction in remote sensing using a polyline process.
C. Lacoste and X. Descombes and J. Zerubia. Pattern Recognition, 43(4): pages 1631-1641, April 2010.
Keywords : Marked point process, Line networks, Road network extraction.
@ARTICLE{lacoste10,
|
| author |
= |
{Lacoste, C. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Unsupervised line network extraction in remote sensing using a polyline process}, |
| year |
= |
{2010}, |
| month |
= |
{April}, |
| journal |
= |
{Pattern Recognition}, |
| volume |
= |
{43}, |
| number |
= |
{4}, |
| pages |
= |
{1631-1641}, |
| url |
= |
{http://dx.doi.org/10.1016/j.patcog.2009.11.003}, |
| keyword |
= |
{Marked point process, Line networks, Road network extraction} |
| } |
Abstract :
Marked point processes provide a rigorous framework to describe a scene by an unordered set of objects. The efficiency of this modeling has been shown on line network extraction with models manipulating interacting segments. In this paper, we extend this previous modeling to polylines composed of an unknown number of segments. Optimization is done via simulated annealing using a Reversible Jump Markov Chain Monte Carlo (RJMCMC) algorithm. We accelerate the convergence of the algorithm by using appropriate proposal kernels. Results on aerial and satellite images show that this new model outperforms the previous one. |
|
4 - Object Extraction Using a Stochastic Birth-and-Death Dynamics in Continuum.
X. Descombes and R. Minlos and E. Zhizhina. Journal of Mathematical Imaging and Vision, 33(3): pages 347-359, 2009.
Keywords : birth and death process, Marked point process, Object extraction.
Copyright : Springer
@ARTICLE{DZM08,
|
| author |
= |
{Descombes, X. and Minlos, R. and Zhizhina, E.}, |
| title |
= |
{Object Extraction Using a Stochastic Birth-and-Death Dynamics in Continuum}, |
| year |
= |
{2009}, |
| journal |
= |
{Journal of Mathematical Imaging and Vision}, |
| volume |
= |
{33}, |
| number |
= |
{3}, |
| pages |
= |
{347-359}, |
| pdf |
= |
{http://dx.doi.org/10.1007/s10851-008-0117-y}, |
| keyword |
= |
{birth and death process, Marked point process, Object extraction} |
| } |
Abstract :
We define a new birth and death dynamics dealing with configurations of disks in the plane. We prove the convergence of the continuous process and propose a discrete scheme converging to the continuous case. This framework is developed to address image processing problems consisting in detecting a configuration of objects from a digital image. The derived algorithm is applied for tree crown extraction and bird detection from aerial images. The performance of this approach is shown on real data. |
|
5 - Building Outline Extraction from Digital Elevation Models using Marked Point Processes.
M. Ortner and X. Descombes and J. Zerubia. International Journal of Computer Vision, 72(2): pages 107-132, April 2007.
Keywords : RJMCMC, Buildings, Stochastic geometry, Marked point process, Digital Elevation Model (DEM).
@ARTICLE{ortner_ijcv_05,
|
| author |
= |
{Ortner, M. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Building Outline Extraction from Digital Elevation Models using Marked Point Processes}, |
| year |
= |
{2007}, |
| month |
= |
{April}, |
| journal |
= |
{International Journal of Computer Vision}, |
| volume |
= |
{72}, |
| number |
= |
{2}, |
| pages |
= |
{107-132}, |
| url |
= |
{http://www.springerlink.com/content/d563v16957427102/?p=873bd324c7c14049a45cc1f2905b5a86&pi=0}, |
| keyword |
= |
{RJMCMC, Buildings, Stochastic geometry, Marked point process, Digital Elevation Model (DEM)} |
| } |
|
 top of the page
5 PhD Thesis and Habilitations |
1 - Shape recognition for image scene analysis.
M. S. Kulikova. PhD Thesis, Universite de Nice - Sophia-Antipolis, December 2009.
Keywords : tree crown , Classification, Shape, multiple object extraction, Marked point process, Shape prior.
@PHDTHESIS{mkulikova_phd09,
|
| author |
= |
{Kulikova, M. S.}, |
| title |
= |
{Shape recognition for image scene analysis}, |
| year |
= |
{2009}, |
| month |
= |
{December}, |
| school |
= |
{Universite de Nice - Sophia-Antipolis}, |
| url |
= |
{http://tel.archives-ouvertes.fr/docs/00/48/20/19/PDF/phd_mkulikova_2009.pdf}, |
| keyword |
= |
{tree crown , Classification, Shape, multiple object extraction, Marked point process, Shape prior} |
| } |
Résumé :
Cette thèse est composée de deux parties principales. La première partie est dédiée au problème de la classification d’espèces d’arbres en utilisant des descripteurs de forme, en combainison ou non, avec ceux de radiométrie ou de texture. Nous montrons notamment que l’information sur la forme améliore la performance d’un classifieur. Pour ce faire, dans un premier temps, une étude des formes de couronnes d’arbres extraites à partir d’images aériennes, en infrarouge couleur, est e ectuée en utilisant une méthodologie d’analyse de
formes des courbes continues fermées dans un espace de formes, en utilisant la notion de chemin géodésique sous deux métriques dans des espaces appropriés : une métrique non-élastique en utilisant la reprèsentation par la fonction d’angle de la courbe, ainsi qu’une métrique élastique induite par une représentation par la racinecarée appelée q-fonction. Une étape préliminaire nécessaire à la classification est l’extraction des couronnes d’arbre. Dans une seconde partie, nous abordons donc le problème de l’extraction d’objets de forme complexe
arbitraire, à partir d’images de télédétection à très haute résolution. Nous construisons un modèle fondé sur les processus ponctuels marqués. Son originalité tient dans sa prise en compte d’objets de forme arbitraire par rapport aux objets de forme paramétrique, e.g. ellipses ou rectangles. Les formes sélectionnées sont obtenues par la minimisation locale d’une énergie de type contours actifs avec di érents a priori sur la forme incorporé. Les objets de la configuration finale (optimale) sont ensuite sélectionnés parmi les candidats par une dynamique
de naissances et morts multiples, couplée à un schéma de recuit simulé. L’approche est validée sur des images de zones forestières à très haute résolution fournies par l’Université d’Agriculture de Suède. |
Abstract :
This thesis includes two main parts. In the first part we address the problem of tree crown classification into species using shape features, without, or in combination with, those of radiometry and texture, to demonstrate that shape information improves classification performance. For this purpose, we first study the shapes of tree crowns extracted from very high resolution colour aerial infra-red images. For our study, we choose a methodology based on the shape analysis of closed continuous curves on shape spaces using geodesic paths under the bending metric with the angle-function curve representation, and the elastic metric with the square root
q-function representation. A necessary preliminary step to classification is extraction of the tree crowns. In the second part, we address thus the problem of extraction of multiple objects with complex, arbitrary shape from remote sensing images of very high resolution. We develop a model based on marked point processes. Its originality lies in its use of arbitrarily-shaped objects as opposed to parametric shape objects, e.g. ellipses or rectangles. The shapes considered are obtained by local minimisation of an active contour energy with weak and then strong shape prior knowledge included. The objects in the final (optimal) configuration are then selected from amongst these candidates by a multiple birth-and-death dynamics embedded in an annealing scheme. The approach is validated on very high resolution images of forest provided by the Swedish University of Agriculture. |
|
2 - Etude du couvert forestier par processus ponctuels marqués.
G. Perrin. PhD Thesis, Ecole Centrale Paris, October 2006.
Keywords : Tree Crown Extraction, Marked point process, Stochastic geometry, Object extraction, RJMCMC.
@PHDTHESIS{perrin_phd06,
|
| author |
= |
{Perrin, G.}, |
| title |
= |
{Etude du couvert forestier par processus ponctuels marqués}, |
| year |
= |
{2006}, |
| month |
= |
{October}, |
| school |
= |
{Ecole Centrale Paris}, |
| url |
= |
{http://www-sop.inria.fr/ariana/personnel/Guillaume.Perrin/resume.php}, |
| pdf |
= |
{http://www-sop.inria.fr/ariana/personnel/Guillaume.Perrin/DOWNLOADS/these_perrin_2006.pdf}, |
| keyword |
= |
{Tree Crown Extraction, Marked point process, Stochastic geometry, Object extraction, RJMCMC} |
| } |
Résumé :
Cette thèse aborde le problème de l'extraction d'arbres à partir d'images aériennes InfraRouge Couleur (IRC) de forêts. Nos modèles reposent sur l'utilisation de processus objets ou processus ponctuels marqués. Il s'agit de variables aléatoires dont les réalisations sont des configurations d'objets géométriques. Une fois l'objet géométrique de référence choisi, nous définissons l'énergie du processus par le biais d'un terme a priori, modélisant les contraintes sur les objets et leurs interactions, ainsi qu'un terme image. Nous échantillonnons le processus objet grâce à un algorithme de type Monte Carlo par Chaînes de Markov à sauts réversibles (RJMCMC), optimisé par un recuit simulé afin d'extraire la meilleure configuration d'objets, qui nous donne l'extraction recherchée.
Dans ce manuscrit, nous proposons différents modèles d'extraction de houppiers, qui extraient des informations à l'échelle de l'arbre selon la densité du peuplement. Dans les peuplements denses, nous présentons un processus d'ellipses, et dans les zones de plus faible densité, un processus d'ellipsoïdes. Nous obtenons ainsi le nombre d'arbres, leur localisation, le diamètre de la couronne et leur hauteur pour les zones non denses. Les algorithmes automatiques résultant de cette modélisation sont testés sur des images IRC très haute résolution fournies par l'Inventaire Forestier National (IFN). |
Abstract :
This thesis addresses the problem of tree crown extraction from Colour InfraRed (CIR) aerial images of forests. Our models are based on object processes, otherwise known as marked point processes. These mathematical objects are random variables whose realizations are configurations of geometrical shapes. This approach yields an energy minimization problem, where the energy is composed of a regularization term (prior density), which introduces some constraints on the objects and their interactions, and a data term, which links the objects to the features to be extracted. Once the reference object has been chosen, we sample the process and extract the best configuration of objects with respect to the energy, using a Reversible Jump Markov Chain Monte Carlo (RJMCMC) algorithm embedded in a Simulated Annealing scheme.
We propose different models for tree crown extraction depending on the density of the stand. In dense areas, we use an ellipse process, while in sparse vegetation an ellipsoïd process is used. As a result we obtain the number of stems, their position, the diameters of the crowns and the heights of the trees for sparse areas. The resulting algorithms are tested on high resolution CIR aerial images provided by the French National Forest Inventory (IFN). |
|
3 - Processus Ponctuels Marqués pour l'Extraction Automatique de Caricatures de Bâtiments à partir de Modèles Numériques d'Elévation.
M. Ortner. PhD Thesis, Universite de Nice Sophia Antipolis, October 2004.
Keywords : Marked point process, Object extraction, Buildings, Digital Elevation Model (DEM), RJMCMC, Stochastic geometry.
@PHDTHESIS{mortner_these,
|
| author |
= |
{Ortner, M.}, |
| title |
= |
{Processus Ponctuels Marqués pour l'Extraction Automatique de Caricatures de Bâtiments à partir de Modèles Numériques d'Elévation}, |
| year |
= |
{2004}, |
| month |
= |
{October}, |
| school |
= |
{Universite de Nice Sophia Antipolis}, |
| url |
= |
{https://hal.inria.fr/tel-00189803}, |
| pdf |
= |
{http://hal.inria.fr/docs/00/18/98/03/PDF/These_Ortner.pdf}, |
| keyword |
= |
{Marked point process, Object extraction, Buildings, Digital Elevation Model (DEM), RJMCMC, Stochastic geometry} |
| } |
Résumé :
Cette thèse se place dans un cadre de reconstruction urbaine et propose un corpus algorithmique pour extraire des formes simples sur les Modèles Numériques d'Elévation. Ce type de données décrit le relief d'une zone urbaine par une grille régulière de points à chacun desquels est associée une information de hauteur.
Les modèles utilisés reposent sur l'utilisation de processus ponctuels marqués. Il s'agit de variables aléatoires dont les réalisations sont des configurations d'objets géométriques. Ces modèles permettent d'introduire des contraintes sur la forme des objets recherchés dans une image ainsi qu'un terme de régularisation modélisé par des interactions entre les objets. Une énergie peut être associée aux configurations d'objets et la configuration minimisant cette énergie trouvée au moyen d'un recuit-simulé couplé à un échantillonneur de type Monte Carlo par Chaîne de Markov à sauts réversibles (RJMCMC).
Nous proposons quatre modèles pour extraire des caricatures de bâtiments à partir de descriptions altimétriques de zones urbaines denses. Chaque modèle est constitué par une forme d'objet, une énergie d'attache aux données et une énergie de régularisation. Les deux premiers modèles permettent d'extraire des formes simples (rectangles) en utilisant une contrainte d'homogénéité pour l'un et une détection des discontinuités pour l'autre. Le troisième modèle modélise les bâtiments par une forme polyhédrique. Le dernier modèle s'intéresse à l'apport d'une coopération entre des objets simples. Les algorithmes obtenus, automatiques, sont évalués sur des données réelles fournies par l'IGN (MNE Laser et optiques de différentes qualités). |
Abstract :
The context of this thesis is the reconstruction of urban areas from images. It proposes a set of algorithms for extracting simple shapes from Digital Elevation Models (DEM). DEMs describe the altimetry of an urban area by a grid of points, each of which has a height associated to it.
The proposed models are based on marked point processes. These mathematical objects are random variables whose realizations are configurations of geometrical shapes. Using these processes, we can introduce constraints on the shape of the objects to be detected in an image, and a regularizing term incorporating geometrical interactions between objects. An energy can be associated to each object configuration, and the global minima of this energy can then be found by applying simulated annealing to a Reversible Jump Monte Carlo Markov Chain sampler (RJMCMC).
We propose four different models for extracting the outlines of buildings from altimetric descriptions of dense urban areas. Each of these models is constructed from an object shape, a data energy, and a regularizing energy.
The first two models extract simple shapes (rectangles) using, respectively, a homogeneity constraint and discontinuity detection. The third model looks for three-dimensional polyhedral buildings. The last model uses cooperation between two types of objects, rectangles and segments.
The resulting algorithms are evaluated on real data provided by the French National Geographic Institute (a laser DEM and optical DEMs of differing quality). |
|
4 - Extraction de Réseaux Linéiques à partir d'Images Satellitaires et Aériennes par Processus Ponctuels Marqués.
C. Lacoste. PhD Thesis, Universite de Nice Sophia Antipolis, September 2004.
Keywords : Stochastic geometry, Object extraction, RJMCMC, Line networks, Simulated Annealing, Marked point process.
@PHDTHESIS{lacoste_these,
|
| author |
= |
{Lacoste, C.}, |
| title |
= |
{Extraction de Réseaux Linéiques à partir d'Images Satellitaires et Aériennes par Processus Ponctuels Marqués}, |
| year |
= |
{2004}, |
| month |
= |
{September}, |
| school |
= |
{Universite de Nice Sophia Antipolis}, |
| url |
= |
{https://hal.inria.fr/tel-00261397}, |
| pdf |
= |
{http://hal.inria.fr/docs/00/26/13/97/PDF/THESE_CAROLINE_LACOSTE.pdf}, |
| keyword |
= |
{Stochastic geometry, Object extraction, RJMCMC, Line networks, Simulated Annealing, Marked point process} |
| } |
Résumé :
Cette thèse aborde le problème de l'extraction non supervisée des réseaux linéiques (routes, rivières, etc.) à partir d'images satellitaires et aériennes. Nous utilisons des processus objet, ou processus ponctuels marqués, comme modèles a priori. Ces modèles permettent de bénéficier de l'apport d'un cadre stochastique (robustesse au bruit, corpus algorithmique, etc.) tout en manipulant des contraintes géométriques fortes. Un recuit simulé sur un algorithme de type Monte Carlo par Chaîne de Markov (MCMC) permet une optimisation globale sur l'espace des configurations d'objets, indépendamment de l'initialisation.
Nous proposons tout d'abord une modélisation du réseau linéique par un processus dont les objets sont des segments interagissant entre eux. Le modèle a priori est construit de façon à exploiter au mieux la topologie du réseau recherché au travers de potentiels fondés sur la qualité de chaque interaction. Les propriétés radiométriques sont prises en compte dans un terme d'attache aux données fondé sur des mesures statistiques.
Nous étendons ensuite cette modélisation à des objets plus complexes. La manipulation de lignes brisées permet une extraction plus précise du réseau et améliore la détection des bifurcations.
Enfin, nous proposons une modélisation hiérarchique des réseaux hydrographiques dans laquelle les affluents d'un fleuve sont modélisés par un processus de lignes brisées dans le voisinage de ce fleuve.
Pour chacun des modèles, nous accélérons la convergence de l'algorithme MCMC par l'ajout de perturbations adaptées.
La pertinence de cette modélisation par processus objet est vérifiée sur des images satellitaires et aériennes, optiques et radar. |
Abstract :
This thesis addresses the problem of the unsupervised extraction of line networks (roads, rivers, etc.) from remotely sensed images. We use object processes, or marked point processes, as prior models. These models benefit from a stochastic framework (robustness w.r.t. noise, algorithms, etc.) while incorporating strong geometric constraints. Optimization is done via simulated annealing using a Reversible Jump Markov Chain Monte Carlo (RJMCMC) algorithm, without any specific initialization.
We first propose to model line networks by a process whose objects are interacting line segments. The prior model is designed to exploit as fully as possible the topological properties of the network under consideration through potentials based on the quality of each interaction. The radiometric properties of the network are modeled using a data term based on statistical measures.
We then extend this model to more complex objects. The use of broken lines improves the detection of network junctions and increases the accuracy of the extracted network.
Finally, we propose a hierarchical model of hydrographic networks in which the tributaries of a given river are modeled by a process of broken lines in the neighborhood of this river. For each model, we accelerate convergence of the RJMCMC algorithm by using appropriate perturbations.
We show experimental results on aerial and satellite images (optical and radar data) to verify the relevance of the object process models. |
|
5 - Processus ponctuels pour l'extraction de réseaux linéiques dans les images satellitaires et aériennes.
R. Stoica. PhD Thesis, Universite de Nice Sophia Antipolis, February 2001.
Keywords : Marked point process, Line networks, Road network, Stochastic geometry, RJMCMC.
@PHDTHESIS{rs01,
|
| author |
= |
{Stoica, R.}, |
| title |
= |
{Processus ponctuels pour l'extraction de réseaux linéiques dans les images satellitaires et aériennes}, |
| year |
= |
{2001}, |
| month |
= |
{February}, |
| school |
= |
{Universite de Nice Sophia Antipolis}, |
| pdf |
= |
{Theses/These-stoica.pdf}, |
| keyword |
= |
{Marked point process, Line networks, Road network, Stochastic geometry, RJMCMC} |
| } |
Résumé :
Les réseaux routiers, ou les réseaux hydrographiques, les vaisseaux sanguins ou bien les fissures dans les matériaux sont connus dans la communauté du traitement d'image sous le nom générique de réseaux liné¨iques. La théorie des processus ponctuels marqués est un cadre mathématique rigoureux qui donne la possibilité de modéliser l'image comme un ensemble d'objets en interaction. Les deux idées principales qui ont motivé ce travail sont : ces réseaux sont approchés par de segments de droite connectés, et les réseaux liné¨iques dans une image sont la réalisation d'un processus ponctuel de Gibbs. Le processus ponctuel qui modèlise les réseaux comporte deux composantes. Le premier terme ("Candy" modèle) gère les états et les interactions entre segments : densité, connectivité, alignement et répulsion des segments. L'emplacement du réseau dans l'image est trouvé grâce au second terme, le terme d'attache aux données. Cette composante du modèle est construite à partir de tests d'hypothèses. L'estimateur des réseaux dans l'image est donné par le minimum d'une fonction d'énergie de Gibbs. Pour trouver l'optimum global de cette fonction, nous mettons en {\oe}uvre un algorithme de type recuit simulé qui s'appuie, sur une dynamique de type Monte Carlo par Chaînes de Markov (MCMC) à sauts réversibles. Des résultats sont présentes sur des images aériennes, SPOT et RADAR (RSO). Nous abordons ensuite deux de problèmes ouverts liés au "Candy" modèle, mais d'un interêt théorique général : la convergence d'une dynamique de Monte Carlo à sauts reversibles, et l'estimation des paramètres des processus ponctuels. Une solution à ces problèmes pourrait ouvrir une nouvelle direction dans la recherche de méthodes non-supervisése en traitement d'image. |
Abstract :
Road or hydrographical networks, blood vessels or fissures in materials are all known by the image processing community under the general name of line networks. The theory of point processes is a rigourous mathematical framework which allows us to model an image as a set of interacting objects. The two main ideas which are the basis of this work are : these networks can be considered as connected segments, and the line networks in an image are the realization of a Gibbs point process. The point process used to model the networks has two components. The first one (Candy model) deals with the states and the interaction of the segments : density, connectivity, alignment, attraction and rejection. The location of the network is determined by the second component, the data term. This component is based on hypothesis tests. The network estimator is given by the minimum of a Gibbs energy. We build a simulated annealing algorithm in order to avoid local minima. This algorithm uses reversible jump Monte Carlo Markov Chain (RJMCMC) dynamics. Results are shown on aerial, SPOT and RADAR (SAR) images. Finally, we start a study on two open problems related to the Candy model, but of general theoretical interest : the convergence of a RJMCMC dynamics, and parameter estimation related to point processes. A solution to these problems would give a new direction for the research of unsupervised methods in image processing. |
|
top of the page
15 Conference articles |
1 - Multiple Birth and Cut Algorithm for Point Process Optimization.
A. Gamal Eldin and X. Descombes and J. Zerubia. In Proc. IEEE International Conference on Signal-Image Technology and Internet-based Systems (SITIS), Kuala Lumpur, Malaysia, December 2010.
Keywords : Multiple Birth and Cut, Graph Cut, Multiple Birth and Death, Marked point process.
@INPROCEEDINGS{MBC_MPP_SITIS10,
|
| author |
= |
{Gamal Eldin, A. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Multiple Birth and Cut Algorithm for Point Process Optimization}, |
| year |
= |
{2010}, |
| month |
= |
{December}, |
| booktitle |
= |
{Proc. IEEE International Conference on Signal-Image Technology and Internet-based Systems (SITIS)}, |
| address |
= |
{Kuala Lumpur, Malaysia}, |
| url |
= |
{http://hal.archives-ouvertes.fr/inria-00516305/fr/}, |
| keyword |
= |
{Multiple Birth and Cut, Graph Cut, Multiple Birth and Death, Marked point process} |
| } |
Abstract :
In this paper, we describe a new optimization method which we call Multiple Birth and Cut (MBC). It combines the recently developed Multiple Birth and Death (MBD) algorithm and the Graph-Cut algorithm. MBD and MBC optimization methods are applied to the energy minimization of an object based model, the marked point process. We compare the MBC to the MBD showing the advantages and disadvantages, where the most important advantage is the reduction of the number of parameters. We validated our algorithm on the counting problem of flamingos in colony, where our algorithm outperforms the performance of the MBD algorithm. |
|
2 - Parameter estimation for a marked point process within a framework of multidimensional shape extraction from remote sensing images.
S. Ben Hadj and F. Chatelain and X. Descombes and J. Zerubia. In Proc. ISPRS Technical Commission III Symposium on Photogrammetry Computer Vision and Image Analysis (PCV), Paris, France, September 2010.
Keywords : Shape extraction, Marked point process, RJMCMC, Simulated Annealing, Stochastic EM (SEM).
@INPROCEEDINGS{sbenhadj10a,
|
| author |
= |
{Ben Hadj, S. and Chatelain, F. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Parameter estimation for a marked point process within a framework of multidimensional shape extraction from remote sensing images}, |
| year |
= |
{2010}, |
| month |
= |
{September}, |
| booktitle |
= |
{Proc. ISPRS Technical Commission III Symposium on Photogrammetry Computer Vision and Image Analysis (PCV)}, |
| address |
= |
{Paris, France}, |
| url |
= |
{http://hal.archives-ouvertes.fr/docs/00/52/63/45/PDF/ISPRS_SBH_FC_XD_JZ_Final2.pdf}, |
| keyword |
= |
{Shape extraction, Marked point process, RJMCMC, Simulated Annealing, Stochastic EM (SEM)} |
| } |
|
3 - Building Detection in a Single Remotely Sensed Image with a Point Process of Rectangles.
C. Benedek and X. Descombes and J. Zerubia. In Proc. International Conference on Pattern Recognition (ICPR), Istanbul, Turkey, August 2010.
Keywords : Marked point process, multiple birth-and-death dynamics, Building extraction.
@INPROCEEDINGS{benedekICPR10,
|
| author |
= |
{Benedek, C. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Building Detection in a Single Remotely Sensed Image with a Point Process of Rectangles}, |
| year |
= |
{2010}, |
| month |
= |
{August}, |
| booktitle |
= |
{Proc. International Conference on Pattern Recognition (ICPR)}, |
| address |
= |
{Istanbul, Turkey}, |
| pdf |
= |
{http://hal.archives-ouvertes.fr/inria-00481019/en/}, |
| keyword |
= |
{Marked point process, multiple birth-and-death dynamics, Building extraction} |
| } |
Abstract :
In this paper we introduce a probabilistic approach of building extraction in remotely sensed images. To cope with data heterogeneity we construct a flexible hierarchical framework which can create various building appearance models from different elementary feature based modules. A global optimization process attempts to find the optimal configuration of buildings, considering simultaneously the observed data, prior knowledge, and interactions between the neighboring building parts. The proposed method is evaluated on various aerial image sets containing more than 500 buildings, and the results are matched against two state-of-the-art techniques. |
|
4 - Extraction of arbitrarily shaped objects using stochastic multiple birth-and-death dynamics and active contours.
M. S. Kulikova and I. H. Jermyn and X. Descombes and E. Zhizhina and J. Zerubia. In Proc. IS&T/SPIE Electronic Imaging, San Jose, USA, January 2010.
Keywords : Object extraction, Marked point process, Shape prior, Active contour, birth-and-death dynamics.
Copyright : Copyright 2010 by SPIE and IS&T. This paper was published in the proceedings of IS&T/SPIE Electronic Imaging 2010 Conference in San Jose, USA, and is made available as an electronic reprint with permission of SPIE and IS&T. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.
@INPROCEEDINGS{Kulikova10a,
|
| author |
= |
{Kulikova, M. S. and Jermyn, I. H. and Descombes, X. and Zhizhina, E. and Zerubia, J.}, |
| title |
= |
{Extraction of arbitrarily shaped objects using stochastic multiple birth-and-death dynamics and active contours}, |
| year |
= |
{2010}, |
| month |
= |
{January}, |
| booktitle |
= |
{Proc. IS&T/SPIE Electronic Imaging}, |
| address |
= |
{San Jose, USA}, |
| pdf |
= |
{http://hal.archives-ouvertes.fr/docs/00/46/54/72/PDF/Kulikova_SPIE2010.pdf}, |
| keyword |
= |
{Object extraction, Marked point process, Shape prior, Active contour, birth-and-death dynamics} |
| } |
Abstract :
We extend the marked point process models that have been used for object extraction from images to arbitrarily shaped objects, without greatly increasing the computational complexity of sampling and estimation. From an alternative point of view, the approach can be viewed as an extension of the active contour methodology to an a priori unknown number of
objects. Sampling and estimation are based on a stochastic birth-and-death process defined on the configuration space of an arbitrary number of objects, where the objects are defined by the image data and prior information. The performance of the approach is demonstrated via experimental results on synthetic and real data. |
|
5 - A marked point process model with strong prior shape information for extraction of multiple, arbitrarily-shaped objects.
M. S. Kulikova and I. H. Jermyn and X. Descombes and E. Zhizhina and J. Zerubia. In Proc. IEEE SITIS, Publ. IEEE Computer Society, Marrakech, Maroc, December 2009.
Keywords : Object extraction, Marked point process, Shape prior, Active contour, multiple birth-and-death dynamics.
@INPROCEEDINGS{Kulikova09a,
|
| author |
= |
{Kulikova, M. S. and Jermyn, I. H. and Descombes, X. and Zhizhina, E. and Zerubia, J.}, |
| title |
= |
{A marked point process model with strong prior shape information for extraction of multiple, arbitrarily-shaped objects}, |
| year |
= |
{2009}, |
| month |
= |
{December}, |
| booktitle |
= |
{Proc. IEEE SITIS}, |
| publisher |
= |
{IEEE Computer Society}, |
| address |
= |
{Marrakech, Maroc}, |
| pdf |
= |
{http://hal.inria.fr/docs/00/43/63/20/PDF/PID1054029.pdf}, |
| keyword |
= |
{Object extraction, Marked point process, Shape prior, Active contour, multiple birth-and-death dynamics} |
| } |
Abstract :
We define a method for incorporating strong prior shape information into a recently extended Markov point process model for the extraction of arbitrarily-shaped objects from images. To estimate the optimal configuration of objects, the process is sampled using a Markov chain based on a stochastic birth-and-death process defined in a space of multiple
objects. The single objects considered are defined by both the image data
and the prior information in a way that controls the computational
complexity of the estimation problem. The method is tested via experiments
on a very high resolution aerial image of a scene composed of tree crowns. |
|
6 - Building Extraction and Change Detection in Multitemporal Remotely Sensed Images with Multiple Birth and Death Dynamics.
C. Benedek and X. Descombes and J. Zerubia. In IEEE Workshop on Applications of Computer Vision (WACV), pages 100-105, Snowbird, Utah, USA, December 2009.
Keywords : Marked point process, Change detection, Aerial images, Building extraction, Satellite images.
@INPROCEEDINGS{benedekWacv09,
|
| author |
= |
{Benedek, C. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Building Extraction and Change Detection in Multitemporal Remotely Sensed Images with Multiple Birth and Death Dynamics}, |
| year |
= |
{2009}, |
| month |
= |
{December}, |
| booktitle |
= |
{IEEE Workshop on Applications of Computer Vision (WACV)}, |
| pages |
= |
{100-105}, |
| address |
= |
{Snowbird, Utah, USA}, |
| pdf |
= |
{http://hal.archives-ouvertes.fr/docs/00/42/66/18/PDF/benedekWACV09.pdf}, |
| keyword |
= |
{Marked point process, Change detection, Aerial images, Building extraction, Satellite images} |
| } |
Abstract :
In this paper we introduce a new probabilistic method which integrates building extraction with change detection in remotely sensed image pairs. A global optimization process attempts to find the optimal configuration of buildings, considering the observed data, prior knowledge, and interactions between the neighboring building parts. The accuracy is ensured by a Bayesian object model verification, meanwhile the computational cost is significantly decreased by a non-uniform stochastic object birth process, which proposes relevant objects with higher probability based on low-level image features.
|
|
7 - Object extraction from high resolution SAR images using a birth and death dynamics.
F. Arslan and X. Descombes and J. Zerubia. In Proc. IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, November 2009.
Keywords : High resolution SAR images, Object extraction, Marked point process, birth and death process.
@INPROCEEDINGS{Fatih09,
|
| author |
= |
{Arslan, F. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Object extraction from high resolution SAR images using a birth and death dynamics}, |
| year |
= |
{2009}, |
| month |
= |
{November}, |
| booktitle |
= |
{Proc. IEEE International Conference on Image Processing (ICIP)}, |
| address |
= |
{Cairo, Egypt}, |
| url |
= |
{http://dx.doi.org/10.1109/ICIP.2009.5413907}, |
| keyword |
= |
{High resolution SAR images, Object extraction, Marked point process, birth and death process} |
| } |
Abstract :
We present a new approach to extract predefined objects, such as trees and oil tanks for instance, from high resolution SAR images. We consider a stochastic approach based on an object process also called marked point process. The objects represent trees or oil tanks which are modeled by disks in the image. We first define a Gibbs density that takes into account both prior information and the data. The energy we define is composed of two terms, one is a prior, penalizing overlaps between objects, and the other is a data term, which measures the suitability of an object in the SAR image. The problem is then reduced to an energy minimization problem. We sample the process to extract the configuration of objects minimizing the energy by a fast birth-and-death dynamics, leading to the total number of objects (trees or oil tanks in our case). This approach is much faster than manual counts and does not need any preprocessing or supervision of a user. |
|
8 - 2D and 3D Vegetation Resource Parameters Assessment using Marked Point Processes.
G. Perrin and X. Descombes and J. Zerubia. In Proc. International Conference on Pattern Recognition (ICPR), Hong-Kong, August 2006.
Keywords : Data energy, Object extraction, Tree Crown Extraction, Stochastic geometry, Marked point process.
@INPROCEEDINGS{perrin_06_c,
|
| author |
= |
{Perrin, G. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{2D and 3D Vegetation Resource Parameters Assessment using Marked Point Processes}, |
| year |
= |
{2006}, |
| month |
= |
{August}, |
| booktitle |
= |
{Proc. International Conference on Pattern Recognition (ICPR)}, |
| address |
= |
{Hong-Kong}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/2006_perrin_06_c.pdf}, |
| keyword |
= |
{Data energy, Object extraction, Tree Crown Extraction, Stochastic geometry, Marked point process} |
| } |
Abstract :
High resolution aerial and satellite images of forests have a key role to play in natural resource management. As they enable to study forests at the scale of trees, it is now possible to get a more accurate evaluation of the forest resources, from which can be deduced information of biodiversity and ecological sustainability. In that prospect, automatic algorithms are needed to give a further exploitation of the data and to assist human operators. In this paper, we present a stochastic geometry approach to extract 2D and 3D parameters of the trees, by modelling the stands as some realizations of a marked point process of ellipses or ellipsoids, whose points are the positions of the trees and marks their geometric features. This approach gives also the number of stems, their position, and their size. It is an energy minimization problem, where the energy embeds a regularization term (prior density), which introduces some interactions between the objects, and a data term, which links the objects to the features to be extracted. Results are shown on aerial images provided by the French National Forest Inventory (IFN). |
|
9 - A comparative study of three methods for identifying individual tree crowns in aerial images covering different types of forests.
M. Eriksson and G. Perrin and X. Descombes and J. Zerubia. In Proc. International Society for Photogrammetry and Remote Sensing (ISPRS), Marne La Vallee, France, July 2006.
Keywords : Region Growing, Marked point process, Markov Fields, Object extraction, Tree Crown Extraction.
@INPROCEEDINGS{eriksson06a,
|
| author |
= |
{Eriksson, M. and Perrin, G. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{A comparative study of three methods for identifying individual tree crowns in aerial images covering different types of forests}, |
| year |
= |
{2006}, |
| month |
= |
{July}, |
| booktitle |
= |
{Proc. International Society for Photogrammetry and Remote Sensing (ISPRS)}, |
| address |
= |
{Marne La Vallee, France}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/2006_eriksson06a.pdf}, |
| keyword |
= |
{Region Growing, Marked point process, Markov Fields, Object extraction, Tree Crown Extraction} |
| } |
Abstract :
Most of today's silviculture methods has the goal to optimise the outcome of the forest in stem volume when it is cut. It might also be relevant to save parts of the forest, for instance, to protect a habitat. In order to get a good survey of the forest, remote sensed images are often used. These images are most often manually interpreted in combination with field measurements in order to estimate the forest parameters that are of importance in the decision how to optimally maintain the forest. Among these parameters the most common are stem number, stem volume, and tree species. Interpretation of images are often labour and time consuming. Thus, automatically developed methods for interpretation can lower the work load and speed up the interpretation time.
The interpretation is often done using images captured from a far distance from the ground in order to capture as large area as possible. However, this lower the accuracy of the estimates since it must be done stand wise. Knowledge of where each individual trees in the forest is located together with its size will increase accuracy. It makes it also possible to plan the cutting in detail. With this knowledge in mind, research about finding automatically methods for finding individual tree crowns in aerial images has been a subject for researchers the last decades.
Today's methods are not capable to alone handle all kind of forests. Therefore, comparative studies of different segmentation methods with different types of forests are of importance in order to clarify how much a method is reliable at a certain type of forest. This knowledge can, for instance, be used to build up an expert system which are supposed to be able to find individual tree crowns in any kind of forests. The comparison is done using images covering different types of forests. The types of forests that are included in the study ranges from isolated tree crown where the ground is clearly visible between the crowns to dense forest which is naturally regenerated via planted forest.
In this study we compare three existing segmentation methods for extracting individual tree crowns from aerial images. The first two methods are probabilistic methods which minimises some energy function while the third is a region growing algorithm. The first probabilistic method is based on a Markov Random Field modelling. We define a prior Markov model to segment the image into three classes (background, vegetation and tree centres). The prior model embed a circular shape model of the tree crown with a random radius. The data term allows to well position the tree centres onto the image and to describe the tree shape as fluctuations around the circular template. Besides, some long range interactions models the relations between the trees locations, such as some periodicity in case of plantations.
The second probabilistic method consists in modeling the trees in the forestry images as random configurations of ellipses or ellipsoids, whose points are the positions of the stems and marks their geometric features. The density of this process embeds a regularization term (prior density), which introduces some interactions between the objects, and a data term, which links the objects to the features to be extracted. We estimate the best configuration of an unknown number of objects, from which 2D and 3D vegetation resource parameters can be extracted. To sample this marked point process, we use Monte Carlo dynamics, while the optimization is performed via a Simulated Annealing algorithm, which results in a fully automatic approach. This approach works well on plantations, where there are high spatial relations between the trees, and on isolated trees where 3D parameters can be extracted, but some difficulties remain in dense areas.
The third method, the region growing algorithm, relies as all region growing methods on good seed points, i.e. in this case approximate locations of the tree crowns. From the seed points the segments are grown according to a grey level value of the neighbouring pixels. The larger the value is the sooner it is connected to the neighbouring segment. The segments stops to grow when all pixels belongs to a segment. This method, contrary the others, will have as a result, segments that have captured the actual shape of the tree crown if the forest is not too sparse. If the forest is too sparse such that the ground is visible, there are problems of finding the seed points. In the cases when the forest is sparse, there are difficulties to separate the tree crowns from the ground. Even if the seed points would be located only at the tree crowns the result will contain a lot of errors since all pixels most belong to a segment, i.e. even the ground pixels must be connected to a segment in this case. |
|
10 - Evaluation des Ressources Forestières à l'aide de Processus Ponctuels Marqués.
G. Perrin and X. Descombes and J. Zerubia. In Proc. Reconnaissance des Formes et Intelligence Artificielle (RFIA), Tours, France, January 2006.
Keywords : Tree Crown Extraction, Stochastic geometry, Marked point process, Object extraction.
@INPROCEEDINGS{perrin_06_a,
|
| author |
= |
{Perrin, G. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Evaluation des Ressources Forestières à l'aide de Processus Ponctuels Marqués}, |
| year |
= |
{2006}, |
| month |
= |
{January}, |
| booktitle |
= |
{Proc. Reconnaissance des Formes et Intelligence Artificielle (RFIA)}, |
| address |
= |
{Tours, France}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/perrin_rfia06.pdf}, |
| keyword |
= |
{Tree Crown Extraction, Stochastic geometry, Marked point process, Object extraction} |
| } |
Résumé :
Les images aériennes et satellitaires jouent un role de plus en plus important dans le domaine de la gestion des ressources naturelles, et en particulier des forêts. Les organismes chargés d'en faire l'inventaire, comme l'Inventaire Forestier National (IFN) en France, s'appuient en effet sur ces images pour observer les différentes espèces d'arbres d'une zone boisée, avant de se rendre sur le terrain pour une étude plus poussée. La résolution submétrique des données permet, en outre, d'entrevoir une étude plus fine, à savoir un comptage à l'arbre près et une classification automatique des houppiers (ensemble des branches et du feuillage d'un arbre). Cette évaluation précise des ressources forestières n'est actuellement pas disponible. Aussi, le développement d'outils automatiques, chargés d'aider les gestionnaires du paysage dans leur travail en leur apportant une connaissance des ressources à l'échelle de l'arbre, se révèle-t-il être d'un intérêt grandissant.L'objectif de notre travail est donc d'extraire des houppiers à partir d'images aériennes de forêts à très haute résolution. Notre approche consiste à modéliser les peuplements forestiers par un processus ponctuel marqué d'ellipses, dont les points représentent les positions des arbres et les marques leurs caractéristiques géométriques. La densité de ce processus comporte une composante de régularisation, dite a priori, qui introduit des interactions entre les objets du processus, ainsi qu'une composante d'attache aux données, afin que les objets du processus se positionnent sur les houppiers que l'on souhaite extraire. Il s'agit de trouver la configuration d'objets, en nombre inconnu a priori, qui maximise cette densité. La simulation de tels processus fait appel aux algorithmes de type Monte Carlo par Chaîne de Markov (MCMC) à sauts réversibles, l'optimisation étant réalisée à l'aide d'un recuit simulé.Nous présentons ici un nouveau modèle d'attache aux données. Contrairement à nos précédents modèles testés sur des plantations, ce modèle n'est plus bayésien puisque le terme d'attache aux données est désormais calculé au niveau des objets et non de l'image. Ceci nous permet de travailler sur des images plus générales, avec des densités d'arbres plus variables. Des résultats obtenus sur des images fournies par l'IFN valident ce modèle. |
Abstract :
Aerial and satellite imagery has a key role to play in natural resources management, especially in forestry application. Indeed, forest inventories, such as the French National Inventory (IFN), refer to these images to analyse the different tree species in a stand, before sending a team on the ground to obtain some more advanced knowledge. Moreover, the submetric resolution of the data enables to study forests at the scale of trees, and also to get a more accurate evaluation of the resources such as the number of stems. It would be also of important economical and environmental concerns to develop automatic tools to analyze and monitor forests.We aim at extracting tree crowns from high resolution aerial images of forests. Our approach consists in modelling the forestry images as realizations of a marked point process of ellipses, whose points are the positions of the trees and marks their geometric features. The density of this process embeds a regularization term (prior density), which introduces some interactions between the objects, and a data term, which links the objects to the features to be extracted. Our goal is to find the best configuration of an unknown number of objects, i.e. the configuration that maximizes this density. To sample the marked point process, we use Monte Carlo dynamics (Reversible Jump Markov Chain Monte Carlo), while the optimization is performed via a simulated annealing algorithm.We present here a new model for the data term. Contrary to our previous models tested on plantations images, this model is not Bayesian anymore : the data term is calculated for each object and not for the whole image. This enables us to work on more general images, with variable tree crown densities. Example results are shown on aerial images provided by the French Forest Inventory (IFN). |
|
11 - Galaxy filament detection using the Quality candy model.
P. Gernez and X. Descombes and J. Zerubia and E. Slezak and A. Bijaoui. In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2006.
Keywords : Marked point process, Quality Candy model, Galaxy Filaments.
@INPROCEEDINGS{gernez06,
|
| author |
= |
{Gernez, P. and Descombes, X. and Zerubia, J. and Slezak, E. and Bijaoui, A.}, |
| title |
= |
{Galaxy filament detection using the Quality candy model}, |
| year |
= |
{2006}, |
| booktitle |
= |
{Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/2006_gernez06.pdf}, |
| keyword |
= |
{Marked point process, Quality Candy model, Galaxy Filaments} |
| } |
|
12 - Adaptive Simulated Annealing for Energy Minimization Problem in a Marked Point Process Application.
G. Perrin and X. Descombes and J. Zerubia. In Proc. Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), St Augustine, Florida, USA, November 2005.
Keywords : Simulated Annealing, Marked point process, Stochastic geometry, MAP estimation, RJMCMC.
Copyright : Springer Verlag
@INPROCEEDINGS{perrin_emmcvpr05,
|
| author |
= |
{Perrin, G. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Adaptive Simulated Annealing for Energy Minimization Problem in a Marked Point Process Application}, |
| year |
= |
{2005}, |
| month |
= |
{November}, |
| booktitle |
= |
{Proc. Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR)}, |
| address |
= |
{St Augustine, Florida, USA}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/perrin_emmcvpr.pdf}, |
| ps |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/perrin_emmcvpr.ps.gz}, |
| keyword |
= |
{Simulated Annealing, Marked point process, Stochastic geometry, MAP estimation, RJMCMC} |
| } |
Abstract :
We use marked point processes to detect an unknown number of trees from high resolution aerial images. This is in fact an energy minimization problem, where the energy contains a prior term which takes into account the geometrical properties of the objects, and a data term to match these objects to the image. This stochastic process is simulated via a Reversible Jump Markov Chain Monte Carlo procedure, which embeds a Simulated Annealing scheme to extract the best configuration of objects.
We compare here different cooling schedules of the Simulated Annealing algorithm which could provide some good minimization in a short time. We also study some adaptive proposition kernels. |
|
13 - A Marked Point Process Model for Tree Crown Extraction in Plantations.
G. Perrin and X. Descombes and J. Zerubia. In Proc. IEEE International Conference on Image Processing (ICIP), Genoa, Italy, September 2005.
Keywords : Stochastic geometry, RJMCMC, Tree Crown Extraction, Object extraction, Marked point process.
@INPROCEEDINGS{perrin_icip05,
|
| author |
= |
{Perrin, G. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{A Marked Point Process Model for Tree Crown Extraction in Plantations}, |
| year |
= |
{2005}, |
| month |
= |
{September}, |
| booktitle |
= |
{Proc. IEEE International Conference on Image Processing (ICIP)}, |
| address |
= |
{Genoa, Italy}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/perrin_icip05.pdf}, |
| ps |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/perrin_icip05.ps.gz}, |
| keyword |
= |
{Stochastic geometry, RJMCMC, Tree Crown Extraction, Object extraction, Marked point process} |
| } |
Abstract :
This work presents a framework to extract tree crowns from remotely sensed data, especially in plantation images, using stochastic geometry. We aim at finding the tree top positions, and the tree crown diameter distribution. Our approach consists in considering that these images are some realizations of a marked point process. First we model the tree plantation as a configuration of an unknown number of ellipses. Then, a Bayesian energy is defined, containing both a prior energy which incorporates the prior knowledge of the plantation geometric properties, and a likelihood which fits the objects to the data. Eventually, we estimate the global minimum of this energy using Reversible Jump Markov Chain Monte Carlo dynamics and a simulated annealing scheme. We present results on optical aerial images of poplars provided by IFN. |
|
14 - Tree Crown Extraction using Marked Point Processes.
G. Perrin and X. Descombes and J. Zerubia. In Proc. European Signal Processing Conference (EUSIPCO), University of Technology, Vienna, Austria, September 2004.
Keywords : RJMCMC, Marked point process, Simulated Annealing, Tree Crown Extraction, Object extraction, Stochastic geometry.
@INPROCEEDINGS{perrin04a,
|
| author |
= |
{Perrin, G. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Tree Crown Extraction using Marked Point Processes}, |
| year |
= |
{2004}, |
| month |
= |
{September}, |
| booktitle |
= |
{Proc. European Signal Processing Conference (EUSIPCO)}, |
| address |
= |
{University of Technology, Vienna, Austria}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/perrin_eusipco2004.pdf}, |
| ps |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/perrin_eusipco2004.ps.gz}, |
| keyword |
= |
{RJMCMC, Marked point process, Simulated Annealing, Tree Crown Extraction, Object extraction, Stochastic geometry} |
| } |
Abstract :
In this paper we aim at extracting tree crowns from remotely sensed images. Our approach is to consider that these images are some realizations of a marked point process. The first step is to define the geometrical objects that design the trees, and the density of the process.
Then, we use a Reversible Jump Markov Chain Monte Carlo dynamics and a simulated annealing to get the maximum a posteriori estimator of the tree crown distribution on the image. Transitions of the Markov chain are managed by some specific proposition kernels.
Results are shown on aerial images of poplars provided by IFN. |
|
15 - Marked Point Process in Image Analysis : from Context to Geometry.
X. Descombes and F. Kruggel and C. Lacoste and M. Ortner and G. Perrin and J. Zerubia. In International Conference on Spatial Point Process Modelling and its Application (SPPA), Castellon, Spain, 2004.
Keywords : RJMCMC, Object extraction, Marked point process, Stochastic geometry.
@INPROCEEDINGS{geostoch04a,
|
| author |
= |
{Descombes, X. and Kruggel, F. and Lacoste, C. and Ortner, M. and Perrin, G. and Zerubia, J.}, |
| title |
= |
{Marked Point Process in Image Analysis : from Context to Geometry}, |
| year |
= |
{2004}, |
| booktitle |
= |
{International Conference on Spatial Point Process Modelling and its Application (SPPA)}, |
| address |
= |
{Castellon, Spain}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/SPPA_2004.pdf}, |
| ps |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/SPPA_2004.ps.gz}, |
| keyword |
= |
{RJMCMC, Object extraction, Marked point process, Stochastic geometry} |
| } |
Abstract :
We consider the marked point process framework as a natural extension of the Markov random field approach in image analysis. We consider a general model defined by its density allowing us to consider some geometrical constraints on objects and between objects in feature extraction problems. Some examples are derived for small brain lesions detection from MR Images, road network, tree crown and building extraction from remotely sensed images. The results obtained on real data show the relevance of the proposal approach. |
|
top of the page
15 Technical and Research Reports |
1 - Estimation des paramètres de modèles de processus ponctuels marqués pour l'extraction d'objets en imagerie spatiale et aérienne haute résolution .
S. Ben Hadj and F. Chatelain and X. Descombes and J. Zerubia. Rapport de recherche 7350, INRIA, July 2010.
Keywords : Marked point process, RJMCMC, Simulated Annealing, Stochastic EM (SEM), pseudo-vraisemblance, Object extraction.
@TECHREPORT{RR-7350,
|
| author |
= |
{Ben Hadj, S. and Chatelain, F. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Estimation des paramètres de modèles de processus ponctuels marqués pour l'extraction d'objets en imagerie spatiale et aérienne haute résolution }, |
| year |
= |
{2010}, |
| month |
= |
{July}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Rapport de recherche}, |
| number |
= |
{7350}, |
| url |
= |
{http://hal.archives-ouvertes.fr/inria-00508431/fr/}, |
| keyword |
= |
{Marked point process, RJMCMC, Simulated Annealing, Stochastic EM (SEM), pseudo-vraisemblance, Object extraction} |
| } |
|
2 - Building Extraction and Change Detection in Multitemporal Aerial and Satellite Images in a Joint Stochastic Approach.
C. Benedek and X. Descombes and J. Zerubia. Research Report 7143, INRIA, Sophia Antipolis, December 2009.
Keywords : Change detection, Building extraction, Marked point process, MAP, multiple birth-and-death dynamics.
@TECHREPORT{benedekRR_09,
|
| author |
= |
{Benedek, C. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Building Extraction and Change Detection in Multitemporal Aerial and Satellite Images in a Joint Stochastic Approach}, |
| year |
= |
{2009}, |
| month |
= |
{December}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{7143}, |
| address |
= |
{Sophia Antipolis}, |
| url |
= |
{http://hal.archives-ouvertes.fr/inria-00426615}, |
| keyword |
= |
{Change detection, Building extraction, Marked point process, MAP, multiple birth-and-death dynamics} |
| } |
Résumé :
Dans ce rapport, nous proposons une nouvelle méthode probabiliste qui intègre l'extraction de bâtiments et la détection de changements à partir de paires d'images de télédétection. Un algorithme d'optimisation globale permet de trouver la configuration optimale de bâtiments en considérant des observations, des connaissances a priori et des interactions entre des parties voisines de bâtiments. La précision est assurée par une vérification d'un modèle objet bayésien; le coût du calcul est considérablement réduit en utilisant un processus stochastique non-uniforme de naissance d'objets fondé sur des caractéristiques bas-niveaux des images, qui génère des objets pertinents ayant une grande probabilité. |
Abstract :
In this report we introduce a new probabilistic method which integrates building extraction with change detection in remotely sensed image pairs. A global optimization process attempts to find the optimal configuration of buildings, considering the observed data, prior knowledge, and interactions between the neighboring building parts. The accuracy is ensured by a Bayesian object model verification, meanwhile the computational cost is significantly decreased by a non-uniform stochastic object birth process, which proposes relevant objects with higher probability based on low-level image features. |
|
3 - Détection de flamants roses par processus ponctuels marqués pour l'estimation de la taille des populations.
S. Descamps and X. Descombes and A. Béchet and J. Zerubia. Research Report 6328, INRIA, October 2007.
Keywords : Object extraction, modélisation stochastique , Marked point process, dynamique de naissance/mort, environnement, flamants roses.
@TECHREPORT{Descamps-Descombes,
|
| author |
= |
{Descamps, S. and Descombes, X. and Béchet, A. and Zerubia, J.}, |
| title |
= |
{Détection de flamants roses par processus ponctuels marqués pour l'estimation de la taille des populations}, |
| year |
= |
{2007}, |
| month |
= |
{October}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{6328}, |
| url |
= |
{http://hal.inria.fr/inria-00180811}, |
| pdf |
= |
{http://hal.inria.fr/docs/00/18/08/93/PDF/RR-Desc-Desc-Bech-Zeru.pdf}, |
| keyword |
= |
{Object extraction, modélisation stochastique , Marked point process, dynamique de naissance/mort, environnement, flamants roses} |
| } |
|
4 - An automatic building extraction method : Application to the 3D-city modeling.
F. Lafarge and P. Trontin and X. Descombes and J. Zerubia and M. Pierrot-Deseilligny. Research Report 5925, INRIA, France, May 2006.
Keywords : Object extraction, Marked point process, 3D reconstruction, Urban areas, Satellite images, Digital Elevation Model (DEM).
@TECHREPORT{lafarge_rr_may06,
|
| author |
= |
{Lafarge, F. and Trontin, P. and Descombes, X. and Zerubia, J. and Pierrot-Deseilligny, M.}, |
| title |
= |
{An automatic building extraction method : Application to the 3D-city modeling}, |
| year |
= |
{2006}, |
| month |
= |
{May}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{5925}, |
| address |
= |
{France}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/2006_lafarge_rr_may06.pdf}, |
| keyword |
= |
{Object extraction, Marked point process, 3D reconstruction, Urban areas, Satellite images, Digital Elevation Model (DEM)} |
| } |
|
5 - A Non-Bayesian Model for Tree Crown Extraction using Marked Point Processes.
G. Perrin and X. Descombes and J. Zerubia. Research Report 5846, INRIA, France, February 2006.
Keywords : Data energy, Object extraction, Tree Crown Extraction, Marked point process, Stochastic geometry, 3D reconstruction.
@TECHREPORT{rr_perrin_nonbay_05,
|
| author |
= |
{Perrin, G. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{A Non-Bayesian Model for Tree Crown Extraction using Marked Point Processes}, |
| year |
= |
{2006}, |
| month |
= |
{February}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{5846}, |
| address |
= |
{France}, |
| url |
= |
{http://hal.inria.fr/inria-00070180/fr/}, |
| pdf |
= |
{http://hal.inria.fr/inria-00070180/fr/}, |
| keyword |
= |
{Data energy, Object extraction, Tree Crown Extraction, Marked point process, Stochastic geometry, 3D reconstruction} |
| } |
Résumé :
Dans ce rapport de recherche, notre but est d'extraire les houppiers à partir d'images aériennes de forêts à l'aide de processus ponctuels marqués d'ellipses ou d'ellipsoïdes. Notre approche consiste, en effet, à modéliser les données comme des réalisations de tels processus. Une fois l'objet géométrique de référence choisi, nous échantillonnons le processus objet défini par une densité grâce à un algorithme MCMC à sauts réversibles, optimisé par un recuit simulé afin d'extraire la meilleure configuration d'objets, qui nous donne l'extraction recherchée.
Nous obtenons ainsi le nombre des arbres, leur localisation et leur taille. Nous présentons, dans ce rapport, un modèle 2D et un modèle 3D pour extraire des statistiques forestières. Ceux-ci sont testés sur des images aériennes infrarouge couleur très haute résolution fournies par l'Inventaire Forestier National (IFN). |
Abstract :
High resolution aerial and satellite images of forests have a key role to play in natural resource management. As they enable forestry managers to study forests at the scale of trees, it is now possible to get a more accurate evaluation of the resources. Automatic algorithms are needed in that prospect to assist human operators in the exploitation of these data. In this paper, we present a stochastic geometry approach to extract 2D and 3D parameters of the trees, by modelling the stands as some realizations of a marked point process of ellipses or ellipsoids, whose points are the locations of the trees and marks their geometric features. As a result we obtain the number of stems, their position, and their size. This approach yields an energy minimization problem, where the energy embeds a regularization term (prior density), which introduces some interactions between the objects, and a data term, which links the objects to the features to be extracted, in 2D and 3D. Results are shown on Colour Infrared aerial images provided by the French National Forest Inventory (IFN) |
|
6 - A Marked Point Process of Rectangles and Segments for Automatic Analysis of Digital Elevation Models..
M. Ortner and X. Descombes and J. Zerubia. Research Report 5712, INRIA, France, October 2005.
Keywords : Marked point process, Buildings, RJMCMC.
@TECHREPORT{ortner-RR05,
|
| author |
= |
{Ortner, M. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{A Marked Point Process of Rectangles and Segments for Automatic Analysis of Digital Elevation Models.}, |
| year |
= |
{2005}, |
| month |
= |
{October}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{5712}, |
| address |
= |
{France}, |
| url |
= |
{https://hal.inria.fr/inria-00070305}, |
| keyword |
= |
{Marked point process, Buildings, RJMCMC} |
| } |
Résumé :
Ce travail présente une approche par géométrie stochastique pour l'extraction de primitives dans les images. Ces structures sont modélisées sous forme de réalisations d'un processus ponctuel spatial marqué dont les points sont des formes géométriques. Cette approche permet d'incorporer un modèle a priori sur la répartition spatiale des structures d'intérêt. Plus spécifiquement, nous présentons un modèle fondé sur l'interaction d'un processus de rectangles avec un processus de segments. Le premier est dédié à la détection des zones homogènes dans l'image et le second à la détection des discontinuités significatives. Nous définissons l'énergie d'une configuration de façon à favoriser la connection entre les segments, l'alignement des rectangles et l'adéquation entre les deux types de primitives. L'estimation repose sur l'emploi d'une technique de recuit-simulé. Le modèle proposé est appliqué à l'analyse de Modèles Numériques d'Elevation. Nous présentons des résultats sur des données réelles fournies par l'Institut Géographique National (IGN). Nous montrons en particulier que l'approche est efficace sur des données de types très différents. |
Abstract :
A marked point process of rectangles and segments for automatic analysis of Digital Elevation Models.
This work presents a framework for automatic feature extraction from images using stochastic geometry. Features in images are modeled as realizations of a spatial point process of geometrical shapes. This framework allows the incorporation of a prior knowledge on the spatial repartition of features. More specifically, we present a model based on the superposition of a process of segments and a process of rectangles. The former is dedicated to the detection of linear networks of discontinuities, while the latter aims at segmenting homogeneous areas. An energy is defined, favoring connections of segments, alignments of rectangles, as well as a relevant interaction between both types of objects. The estimation is performed by minimizing the energy using a simulated annealing algorithm. The proposed model is applied to the analysis of Digital Elevation Models (DEMs). These images are raster data representing the altimetry of a dense urban area. We present results on real data provided by the IGN (French National Geographic Institute) consisting in low quality DEMs of various types. |
|
7 - Optimization Techniques for Energy Minimization Problem in a Marked Point Process Application to Forestry.
G. Perrin and X. Descombes and J. Zerubia. Research Report 5704, INRIA, France, September 2005.
Keywords : Simulated Annealing, Marked point process, Stochastic geometry, Optimization.
@TECHREPORT{rr_perrin_optim_05,
|
| author |
= |
{Perrin, G. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Optimization Techniques for Energy Minimization Problem in a Marked Point Process Application to Forestry}, |
| year |
= |
{2005}, |
| month |
= |
{September}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{5704}, |
| address |
= |
{France}, |
| url |
= |
{https://hal.inria.fr/inria-00070312}, |
| pdf |
= |
{https://hal.inria.fr/file/index/docid/70312/filename/RR-5704.pdf}, |
| ps |
= |
{https://hal.inria.fr/docs/00/07/03/12/PS/RR-5704.ps}, |
| keyword |
= |
{Simulated Annealing, Marked point process, Stochastic geometry, Optimization} |
| } |
Résumé :
Dans ce rapport de recherche, nous utilisons les processus ponctuels marqués afin d'extraire un nombre inconnu d'objets dans des images aériennes. Ces processus sont définis par une énergie, qui contient un terme a priori formalisant les interactions entre objets ainsi qu'un terme d'attache aux données. Nous cherchons à minimiser cette énergie, afin d'obtenir la meilleure configuration d'objets, à l'aide d'un recuit simulé qui s'inscrit dans l'algorithme d'échantillonnage MCMC à sauts réversibles.
Nous comparons ici différents schémas de décroissance de température, et présentons certaines méthodes qui permettent d'améliorer la convergence de l'algorithme en un temps fini. |
Abstract :
We use marked point processes to detect an unknown number of trees from high resolution aerial images. This approach turns to be an energy minimization problem, where the energy contains a prior term which takes into account the geometrical properties of the objects, and a data term to match these objects onto the image. This stochastic process is simulated via a Reversible Jump Markov Chain Monte Carlo procedure, which embeds a Simulated Annealing scheme to extract the best configuration of objects.
We compare in this paper different cooling schedules of the Simulated Annealing algorithm which could provide some good minimization in a short time. We also study some adaptive proposition kernels. |
|
8 - Point Processes in Forestry : an Application to Tree Crown Detection.
G. Perrin and X. Descombes and J. Zerubia. Research Report 5544, INRIA, France, April 2005.
Keywords : Marked point process, Object extraction, RJMCMC, Tree Crown Extraction, Stochastic geometry.
@TECHREPORT{5544,
|
| author |
= |
{Perrin, G. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Point Processes in Forestry : an Application to Tree Crown Detection}, |
| year |
= |
{2005}, |
| month |
= |
{April}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{5544}, |
| address |
= |
{France}, |
| url |
= |
{https://hal.inria.fr/inria-00070463}, |
| pdf |
= |
{https://hal.inria.fr/file/index/docid/70463/filename/RR-5544.pdf}, |
| ps |
= |
{https://hal.inria.fr/docs/00/07/04/63/PS/RR-5544.ps}, |
| keyword |
= |
{Marked point process, Object extraction, RJMCMC, Tree Crown Extraction, Stochastic geometry} |
| } |
Résumé :
Dans ce rapport de recherche, notre but est d'extraire des houppiers à partir d'images aériennes de forêts à l'aide de processus ponctuels marqués de disques et d'ellipses. Notre approche consiste, en effet, à modéliser les données comme des réalisations de tels processus. Une fois l'objet géométrique de référence choisi, nous échantillonnons le processus objet défini par une densité grâce à un algorithme MCMC à sauts réversibles, optimisé par un recuit simulé afin d'extraire le maximum a posteriori de cette densité. Cette configuration optimale nous donnera l'extraction recherchée.
Dans une première partie, nous proposons de revenir quelque peu sur les processus ponctuels marqués et leur application dans la foresterie. Puis, nous présentons deux nouveaux modèles d'extraction de houppiers à base de disques et d'ellipses, et discutons de quelques améliorations au niveau de la simulation et de l'optimisation de notre algorithme.
Nous présentons des résultats obtenus sur des images aériennes très haute résolution fournies par l'Inventaire Forestier National (IFN), ainsi que sur des images synthétiques simulées avec le logiciel AMAP (Bionatics, projet Digiplante). |
Abstract :
In this research report, we aim at extracting tree crowns from remotely sensed images using marked point processes of discs and ellipses. Our approach is indeed to consider that the data are some realizations of a marked point process. Once a geometrical object is defined, we sample a marked point process defined by a density with a Reversible Jump Markov Chain Monte Carlo dynamics and simulated annealing to get the maximum a posteriori estimator of the tree crown distribution on the image.
In a first part, we propose to review the basis of marked point processes and some of their examples used in forestry statistic inference. Then, we present two new models, with discs and ellipses, and discuss some improvements made in the optimization or in the simulation.
Results are shown on high resolution aerial images of poplars provided by the French Forest Inventory (IFN), and synthetic images simulated with AMAP software (Bionatics, Digiplante project). |
|
9 - Extraction de Houppiers par Processus Objet.
G. Perrin and X. Descombes and J. Zerubia. Research Report 5037, INRIA, France, December 2003.
Keywords : Object extraction, Tree Crown Extraction, Stochastic geometry, Marked point process, RJMCMC.
@TECHREPORT{Perrin03,
|
| author |
= |
{Perrin, G. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Extraction de Houppiers par Processus Objet}, |
| year |
= |
{2003}, |
| month |
= |
{December}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{5037}, |
| address |
= |
{France}, |
| url |
= |
{https://hal.inria.fr/inria-00071547}, |
| pdf |
= |
{https://hal.inria.fr/file/index/docid/71547/filename/RR-5037.pdf}, |
| ps |
= |
{https://hal.inria.fr/docs/00/07/15/47/PS/RR-5037.ps}, |
| keyword |
= |
{Object extraction, Tree Crown Extraction, Stochastic geometry, Marked point process, RJMCMC} |
| } |
Résumé :
Nous cherchons à extraire des houppiers à partir d'images de télédétection. Pour ce faire, nous construisons un processus objet et assimilons nos images d'arbres à des réalisations de ce processus. La première étape consiste à définir d'une part les objets géométriques modélisant les arbres, et d'autre part la densité du processus à simuler.La seconde étape consiste à construire un algorithme MCMC à sauts réversibles, et une estimée de la configuration d'objets. Les transitions aléatoires de la chaîne sont régies par des noyaux de propositions, chacun étant associé à une perturbation.Nous testons notre modèle sur des images aériennes de peupleraies fournies par l'IFN. |
Abstract :
In this paper we aim at extracting tree crowns from remotely sensed images. Our approach is to consider that these images are some realizations of a marked point process. The first step is to define the geometrical objects that design the trees, and the density of the process.Then, we use a reversible jump MCMC dynamics and a simulated annealing to get the maximum a posteriori estimator of the tree crowns distribution on the image. Transitions of the Markov chain are managed by some specific proposition kernels.Results are shown on aerial images of poplars given by IFN. |
|
10 - Automatic 3D Land Register Extraction from Altimetric Data in Dense Urban Areas.
M. Ortner and X. Descombes and J. Zerubia. Research Report 4919, INRIA, France, September 2003.
Keywords : Object extraction, Buildings, RJMCMC, Stochastic geometry, Digital Elevation Model (DEM), Marked point process.
@TECHREPORT{4919,
|
| author |
= |
{Ortner, M. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Automatic 3D Land Register Extraction from Altimetric Data in Dense Urban Areas}, |
| year |
= |
{2003}, |
| month |
= |
{September}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{4919}, |
| address |
= |
{France}, |
| url |
= |
{https://hal.inria.fr/inria-00071660}, |
| pdf |
= |
{https://hal.inria.fr/file/index/docid/71660/filename/RR-4919.pdf}, |
| ps |
= |
{https://hal.inria.fr/docs/00/07/16/60/PS/RR-4919.ps}, |
| keyword |
= |
{Object extraction, Buildings, RJMCMC, Stochastic geometry, Digital Elevation Model (DEM), Marked point process} |
| } |
Résumé :
Ce travail présente un algorithme qui extrait automatiquement un plan cadastral de la description altimétrique (relief) d'une zone urbaine dense. L'altimétrie d'une ville est une donnée qui est maintenant facilement accessible. Dans ce rapport, nous présentons par exemple des résultats sur deux types de données altimétriques : le premier consiste en un Modèle Numérique d'Elévation (MNE) obtenu par corrélation d'images optiques, le second correspond à un MNE obtenu par mesure LASER.Notre objectif principal est de définir un algorithme entièrement automatique capable d'extraire un grand nombre de bâtiments dans des zones urbaines denses.Nous nous intéressons donc plus particulièrement à l'extraction de formes élémentaires et proposons un algorithme qui modélise les bâtiments par des formes rectangulaires. Le résultat obtenu consiste en une carte cadastrale qui peut être utilisée pour faire une estimation précise des formes de toits, par exemple.L'algorithme proposé ici repose sur nos travaux précédents. Nous modélisons des villes par des configurations de rectangles auxquelles nous associons une énergie définie de manière à tenir compte aussi bien d'une information de bas niveau provenant des données utilisées que d'une connaissance géometrique de l'agencement des bâtiments dans les zones urbaines.L'estimation est ensuite faite en minimisant l'énergie définie grace à un recuit-simulé.Nous utilisons un échantilloneur MCMC qui est une combinaison de techniques générales de type Metropolis Hastings Green et de l'algorithme de simulation de processus ponctuel proposé par Geyer et Møller. Nous utilisons en particulier des noyaux de proposition originaux comme la naissance ou mort dans un voisinage, et nous définissons l'énergie par rapport à un processus ponctuel de Poisson non-homogène, ce qui permet d'améliorer le comportement dynamique de l'algorithme.Les resultats que nous présentons sont obtenus sur des donnée réelles fournies par l'IGN. Nous extrayons automatiquement des configurations composées d'une centaine de bâtiments sur des zones dont la taille est en moyenne de 200m sur 200m. L'erreur commise est en moyenne de 15. |
Abstract :
This work present an automatic algorithm that extract 3D land register from altimetric data in dense urban areas. Altimetry of a town is a data which is easily available yet difficult to exploit. For instance, we present here results on two kind of measurements : the first one consists in a Digital Elevation Model (DEM) built using a correlation algorithm and some optical data, while the second one consists in a DEM obtained by Laser measurments.Our main objective is to design an entirely automatic method that is able to deal with this kind of data in very dense urban areas.We thus focus on elementary shape extraction and propose an algorithm that extracts rectangular buildings. The result provided consists in a kind of vectorial land register map that can be used, for instance, to perform precise roof shape estimation.The proposed algorithm uses our previous work. Using a point process framework, we model towns as configuration of rectangles. An energy is defined, that takes into account both a low level information provided by the altimetry of the scene, and some geometric knowledge of the disposition of buildings in towns.The estimation is done by minimizing the energy using a simulated annealing. We use a MCMC sampler that is a combination of general Metropolis Hastings Green techniques and Geyer and Møller algorithm of sampling of point processes. We use some original proposition kernels, such as birth or death in a neighborhood and define the energy with respect to an inhomogeneous Poisson point process.We present results on real data provided by IGN (French Mapping Institute). Results were automatically obtained, on areas that are 200m by 200m large. These results consist in configurations of around 100 rectangles describing considered areas with an error of 15 missclassification. |
|
11 - Improved RJMCMC Point Process Sampler for Object Detection by Simulated Annealing.
M. Ortner and X. Descombes and J. Zerubia. Research Report 4900, INRIA, France, August 2003.
Keywords : Buildings, Object extraction, RJMCMC, Marked point process.
@TECHREPORT{4900,
|
| author |
= |
{Ortner, M. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Improved RJMCMC Point Process Sampler for Object Detection by Simulated Annealing}, |
| year |
= |
{2003}, |
| month |
= |
{August}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{4900}, |
| address |
= |
{France}, |
| url |
= |
{https://hal.inria.fr/inria-00071683}, |
| pdf |
= |
{https://hal.inria.fr/file/index/docid/71683/filename/RR-4900.pdf}, |
| ps |
= |
{https://hal.inria.fr/docs/00/07/16/83/PS/RR-4900.ps}, |
| keyword |
= |
{Buildings, Object extraction, RJMCMC, Marked point process} |
| } |
Résumé :
Nous commen ons par résumer l'algorithme de Geyer et Møller qui permet, en utilisant une chaîne de Markov, d'échantillonner des lois de processus ponctuels. Nous rappelons également le cadre théorique proposé par Green qui permet d'imposer la réversibilité d'une chaîne de Markov sous une loi désirée.Dans le cadre de nos applications en traitement d'image, nous sommes intéressés par la simulation de processus ponctuels dont la loi dépend fortement de la localisation géographique des points. Nous présentons donc ici des noyaux de proposition qui améliorent la capacité de l'algorithme de Geyer et Meyer à explorer les bons endroits de l'espace d'état. En particulier, nous proposons une transformation qui permet de faire apparaître ou disparaître des points dans un voisinage quelconque d'un autre point. Nous gardons également la possibilité de générer des points suivant une loi non uniforme.Nous construisons donc de tels noyaux de perturbations grâce au travail de Green de manière à garder la-(.) réversibilité de la chaîne de Markov construite. Nous démontrons ensuite les bonnes propriétés de stabilité qui assurent le bon comportement asymptotique de la chaîne. En particulier, grâce à une condition de «drift», nous montrons l'ergodicité géométrique et la récurrence de la chaîne au sens de Harris.Nous concluons en validant par l'expérience nos résultats théoriques, et en montrons leur utilité sur un exemple concret.Nous proposons d'ultimes améliorations pour conclure. |
Abstract :
We first recall Geyer and Møller algorithm that allows to sample point processes using a Markov chain. We also recall Green's framework that allows to build samplers on general state spaces by imposing reversibility of the designed Markov chain.Since in our image processing applications, we are interested by sampling highly spatially correlated and non-invariant point processes, we adapt these ideas to improve the exploration ability of the algorithm. In particular, we keep the ability of generating points with non-uniform distributions, and design an updating scheme that allows to generate points in some neighborhood of other points. We first design updating schemes under Green's framework to keep (.) reversibility of the Markov chain and then show that stability properties are not loosed. Using a drift condition we prove that the Markov chain is geometrically ergodic and Harris recurrent.We finally show on experimental results that these kinds of updates are usefull and propose other improvements. |
|
12 - A Comparative Study of Point Processes for Line Network Extraction in Remote Sensing.
C. Lacoste and X. Descombes and J. Zerubia. Research Report 4516, Inria, France, July 2002.
Keywords : Stochastic geometry, Marked point process, Road network, Line networks, RJMCMC.
@TECHREPORT{4516,
|
| author |
= |
{Lacoste, C. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{A Comparative Study of Point Processes for Line Network Extraction in Remote Sensing}, |
| year |
= |
{2002}, |
| month |
= |
{July}, |
| institution |
= |
{Inria}, |
| type |
= |
{Research Report}, |
| number |
= |
{4516}, |
| address |
= |
{France}, |
| url |
= |
{http://hal.inria.fr/inria-00072072}, |
| pdf |
= |
{http://hal.inria.fr/docs/00/07/20/72/PDF/RR-4516.pdf}, |
| ps |
= |
{http://hal.inria.fr/docs/00/07/20/72/PS/RR-4516.ps}, |
| keyword |
= |
{Stochastic geometry, Marked point process, Road network, Line networks, RJMCMC} |
| } |
Résumé :
Nous présentons, dans ce rapport, une étude comparative entre plusieurs modèles d'extraction de réseaux linéiques, issus de la géométrie stochastique. Nous nous pla ons dans le cadre des processus ponctuels marqués spécifiés par une densité par rapport au processus de Poisson homogène. L'objectif de cette étude est de déterminer quelle type de densité a priori est la plus adaptée à cette probématique de détection de réseaux linéiques, et plus particulièrement de réseaux routiers. Nous reprenons le Candy modèle, introduit dans [21] pour l'extraction de réseaux routiers, et nous l'utilisons comme modèle de référence. Ce modèle est basé sur l'idée qu'un réseau routier peut être assimilé à une réalisation d'un processus Markov objet, où les objets correspondent à des segments en interaction. Nous proposons deux variantes de ce modèle qui font intervenir des coefficients mesurant la qualité des interactions entre objets. La première est une généralisation du Candy modèle et la seconde correspond à une adaptation du modèle IDQ, proposé dans [13] pour l'extraction de bâtiments dans les modèles numériques d'élévation. Nous réalisons l'optimisation de chaque modèle par un recuit simulé sur un algorithme MCMC à sauts réversibles. Les résultats expérimentaux obtenus pour les trois modèles, sur des images satellitaires ou aériennes, permettent de vérifier l'intérêt de l'intégration de la qualité des interactions dans la densité a priori. |
Abstract :
We present in this report a comparative study between models of line network extraction, within a stochastic geometry framework. We rely on the theory of marked point processes specified by a density with respect to the uniform Poisson process. We aim to determine which prior density is the most relevant for road network detection. The Candy model, introduced in [21] for the extraction of road networks, is used as a reference model. This model is based on the idea that a road network can be thought of as a realization of a Markov object process, where the objects correspond to interacting line segments. We have developed two variants of this model which use quality coefficients for interactions. The first of these two variants is a generalization of the Candy model and the second one is an adaptation of the IDQ model proposed in [13] for the problem of building extraction from digital elevation models. The optimization is achieved by a simulated annealing with a RJMCMC algorithm. The experimental results, obtained for each model on aerial or satellite images, show the interest of adding quality coefficients for interactions in the prior density. |
|
13 - Building detection by markov object processes and a MCMC algorithm.
L. Garcin and X. Descombes and J. Zerubia and H. Le Men. Research Report 4206, Inria, France, June 2001.
Keywords : Stochastic geometry, Marked point process, Buildings, RJMCMC.
@TECHREPORT{xd01a,
|
| author |
= |
{Garcin, L. and Descombes, X. and Zerubia, J. and Le Men, H.}, |
| title |
= |
{Building detection by markov object processes and a MCMC algorithm}, |
| year |
= |
{2001}, |
| month |
= |
{June}, |
| institution |
= |
{Inria}, |
| type |
= |
{Research Report}, |
| number |
= |
{4206}, |
| address |
= |
{France}, |
| url |
= |
{https://hal.inria.fr/inria-00072416}, |
| pdf |
= |
{https://hal.inria.fr/file/index/docid/72416/filename/RR-4206.pdf}, |
| ps |
= |
{https://hal.inria.fr/docs/00/07/24/16/PS/RR-4206.ps}, |
| keyword |
= |
{Stochastic geometry, Marked point process, Buildings, RJMCMC} |
| } |
Résumé :
Le but de ce travail est de détecter les bâtiments à partir de photographies aeriennes numériques. Nous modélisons un ensemble de bâtiments par une configuration d'objets. Nous définissons un processus ponctuel sur l'ensemble des configurations qui se décompose en deux parties :
* La première est un modèle a priori sur les configurations qui considère des interactions entre les objets,
* la seconde est un modèle d'attache aux données qui induit la cohérence du résultat avec l'image traitée.
Nous avons ainsi une distribution a posteriori dont nous recherchons la configuration maximale. Pour obtenir ce maximum, nous utilisons une simulatio- n de type MCMC - un algorithme de Metropolis-Hasting-Green- couplée avec un schéma de recuit simulé. Nous testons la méthode décrite à la fois sur des données synthétiques et des images stéréoscopiques réelles. |
Abstract :
This work aims at detecting buildings in digital aerial photographs. Here we model a set of buildings by a configuration of objects. We define a point process on the set of configurations, which splits into two parts :
* the first one is a prior model on the configurations which use interactions between objects,
* the second one is a data model which enforces the coherence with the image.
Thus we have a posterior distribution whose maximum has to be found. In order to achieve this maximum, we use a MCMC simulation - a Metropolis-Hasting- s-Green algorithm - mixed with a simulated annealing. Then we test this method on both synthetic and real stereo-images. |
|
14 - Simulation de processus objets : Etude de faisabilité pour une application à la segmentation d'image.
M. Imberty and X. Descombes. Research Report 3881, Inria, February 2000.
Keywords : Marked point process, Stochastic geometry, Segmentation.
@TECHREPORT{xd00im,
|
| author |
= |
{Imberty, M. and Descombes, X.}, |
| title |
= |
{Simulation de processus objets : Etude de faisabilité pour une application à la segmentation d'image}, |
| year |
= |
{2000}, |
| month |
= |
{February}, |
| institution |
= |
{Inria}, |
| type |
= |
{Research Report}, |
| number |
= |
{3881}, |
| url |
= |
{https://hal.inria.fr/inria-00072772}, |
| pdf |
= |
{https://hal.inria.fr/file/index/docid/72772/filename/RR-3881.pdf}, |
| ps |
= |
{https://hal.inria.fr/docs/00/07/27/72/PS/RR-3881.ps}, |
| keyword |
= |
{Marked point process, Stochastic geometry, Segmentation} |
| } |
Résumé :
Dans cette étude, nous comparons l'efficacité de deux techniques de simulation par chaînes de Markov (MCMC) de processus aléatoires sur des ensembles d'objets géométriques : l'algorithme de naissance-mort et celui de Metropolis-- Hastings-Green. Les comparaisons sont effectuées sur différents modèles de processus objets de type attractif présentant un intérêt en traitement d'image. Nous appliquons ensuite ces méthodes de simulation à la segmentation d'image. Pour cela, nous nous plaçons dans le cadre bayésien : nous définisson- s donc un modèle a priori attractif simple sur des objets rectangulaires, ainsi qu'un terme d'attache aux données garantissant l'adéquation des objets à l'image. Nous utilisons ensuite un recuit simulé pour extraire les différentes zones de l'image. Des tests sont effectués sur des images synthétiques. |
Abstract :
In this study, we compare the efficiency of two algorithms using Monte Carlo Markov chains methods in order to simulate random processes of geometric- al objects sets : the algorithm of birth and death and the dynamics of Metropolis-Hastings-Green. The comparisons are carried out on various object models for clustered patterns, which could be of interest in image processing. Then we apply these methods of simulation to image segmentation, using the bayesian approach : thus we define a simple prior model on rectangul- ar objects, as well as a posterior probability guaranteeing the adequacy of the objects to the data. We finally use a stochastic annealing to extract the various zones of the image. Some tests are performed on synthetic data. |
|
15 - A Markov point process for road extraction in remote sensed images.
R. Stoica and X. Descombes and J. Zerubia. Research Report 3923, Inria, 2000.
Keywords : Stochastic geometry, Marked point process, Candy model, Road network, RJMCMC.
@TECHREPORT{rs00,
|
| author |
= |
{Stoica, R. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{A Markov point process for road extraction in remote sensed images}, |
| year |
= |
{2000}, |
| institution |
= |
{Inria}, |
| type |
= |
{Research Report}, |
| number |
= |
{3923}, |
| url |
= |
{https://hal.inria.fr/inria-00072729}, |
| pdf |
= |
{https://hal.inria.fr/file/index/docid/72729/filename/RR-3923.pdf}, |
| ps |
= |
{https://hal.inria.fr/docs/00/07/27/29/PS/RR-3923.ps}, |
| keyword |
= |
{Stochastic geometry, Marked point process, Candy model, Road network, RJMCMC} |
| } |
Résumé :
Nous proposons une nouvelle méthode pour extraire les routes dans les images satellitales et aériennes. Notre approche est basée sur la géométrie stochastique et les dynamiques MCMC à saut réversible. Nous considérons que le réseau routier est un réseau fin, et que ce réseau peut être approximé par des segments connectés. Nous construisons un processus ponctuel marqué qui peut simuler et détecter des réseaux fins. La densité de probabilité de ce processus comporte deux termes : le terme d'attache aux données et le terme a priori. Pour former un réseau, les segments doivent être connectés. Nous souhaitons que les segments soient bien alignés et qu'ils ne se superposent pas. Toutes ces contraintes sont prises en compte par le modèle a priori (Candy modèle). L'emplacement du réseau est donné par le terme d'attache aux données. Ce terme est construit à partir des tests d'hypothèses. Notre modèle probabiliste permet de construire le MAP de l'estimateur du réseau linéique. Pour éviter les minima locaux, nous utilisons un algorithme de type recuit simulé, construit sur une dynamique MCMC à sauts réversibles. Nous montrons des résultats sur des images SPOT, ERS et aériennes. |
Abstract :
In this paper we propose a new method to extract roads in remote sensed images. Our approach is based on stochastic geometry theory and reversible jump Monte Carlo Markov Chains dynamic. We consider that roads consist of a thin network in the image. We make the hypothesis that such a network can be approximated by a network composed of connected line segments. We build a marked point process, which is able to simulate and detect thin networks. The segments have to be connected, in order to form a line-netw- ork. Aligned segments are favored whereas superposition is penalized. Those constraints are taken in account by the prior model (Candy model), which is an area-interaction point process.The location of the network and the specifities of a road network in the image are given by the likelihood term. This term is based on statistical hypothesis tests. The proposed probabilistic model yelds a MAP estimator of the road network. In order to avoid local minima, a simulated annealing algorithm, using a reversible jump MCMC dynamic is designed. Results are shown on SPOT, ERS and aerial images. |
|
top of the page
2 Collection articles or Books chapters |
1 - A Reversible Jump MCMC Sampler for Object Detection in Image Processing.
M. Ortner and X. Descombes and J. Zerubia. In Monte Carlo and Quasi-Monte Carlo Methods, Publ. Springer Verlag, 2005.
Keywords : RJMCMC, Marked point process, Object extraction.
@INCOLLECTION{ortner_lnsmc2qmc,
|
| author |
= |
{Ortner, M. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{A Reversible Jump MCMC Sampler for Object Detection in Image Processing}, |
| year |
= |
{2005}, |
| booktitle |
= |
{Monte Carlo and Quasi-Monte Carlo Methods}, |
| publisher |
= |
{Springer Verlag}, |
| url |
= |
{http://link.springer.com/book/10.1007/3-540-31186-6}, |
| pdf |
= |
{http://link.springer.com/chapter/10.1007%2F3-540-31186-6_23}, |
| keyword |
= |
{RJMCMC, Marked point process, Object extraction} |
| } |
|
2 - An application of marked point process to the extraction of linear networks for images.
R. Stoica and X. Descombes and M.N.M. Van Lieshout and J. Zerubia. In Spatial statitics through applications, Publ. WITPress, 2002.
Keywords : Line networks, Road network, Object extraction, Satellite images, Marked point process.
@INCOLLECTION{stoicaXDlivre,
|
| author |
= |
{Stoica, R. and Descombes, X. and Van Lieshout, M.N.M. and Zerubia, J.}, |
| title |
= |
{An application of marked point process to the extraction of linear networks for images}, |
| year |
= |
{2002}, |
| booktitle |
= |
{Spatial statitics through applications}, |
| publisher |
= |
{WITPress}, |
| url |
= |
{http://www.witpress.com/books/978-1-85312-649-9}, |
| pdf |
= |
{http://oai.cwi.nl/oai/asset/10645/10645A.pdf}, |
| keyword |
= |
{Line networks, Road network, Object extraction, Satellite images, Marked point process} |
| } |
|
top of the page
These pages were generated by 
|
New demo webpage
get the bibtex
