Publications about Road network

Result of the query in the list of publications :

• 3 Articles
• 3 PhD Thesis and Habilitations
• 9 Conference articles
• 6 Technical and Research Reports
• 1 Collection article or Book chapter

new search | get the bibtex

navigation : 1 - 2 - 3 display : 10 per page | 20 per page | 50 per page

3 Articles

1 - Incorporating generic and specific prior knowledge in a multi-scale phase field model for road extraction from VHR images. T. Peng and I. H. Jermyn and V. Prinet and J. Zerubia. IEEE Trans. Geoscience and Remote Sensing, 1(2): pages 139--146, June 2008. Keywords : Dense urban areas, Geographic Information System (GIS), Multiscale, Road network, Variational methods, Very high resolution. Copyright : ©2008 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. @ARTICLE{Peng08b, author = {Peng, T. and Jermyn, I. H. and Prinet, V. and Zerubia, J.}, title = {Incorporating generic and specific prior knowledge in a multi-scale phase field model for road extraction from VHR images}, year = {2008}, month = {June}, journal = {IEEE Trans. Geoscience and Remote Sensing}, volume = {1}, number = {2}, pages = {139--146}, url = {http://dx.doi.org/10.1109/JSTARS.2008.922318}, pdf = {http://www-sop.inria.fr/members/Ian.Jermyn/publications/PengetalTGRS08.pdf}, keyword = {Dense urban areas, Geographic Information System (GIS), Multiscale, Road network, Variational methods, Very high resolution} } Abstract : This paper addresses the problem of updating digital road maps in dense urban areas by extracting the main road network from very high resolution (VHR) satellite images. Building on the work of Rochery et al. (2005), we represent the road region as a 'phase field'. In order to overcome the difficulties due to the complexity of the information contained in VHR images, we propose a multi-scale statistical data model. It enables the integration of segmentation results from coarse resolution, which furnishes a simplified representation of the data, and fine resolution, which provides accurate details. Moreover, an outdated GIS digital map is introduced into the model, providing specific prior knowledge of the road network. This new term balances the effect of the generic prior knowledge describing the geometric shape of road networks (i.e. elongated and of low-curvature) carried by a 'phase field higher-order active contour' term. Promising results on QuickBird panchromatic images and comparisons with several other methods demonstrate the effectiveness of our approach.

2 - Higher-Order Active Contour Energies for Gap Closure. M. Rochery and I. H. Jermyn and J. Zerubia. Journal of Mathematical Imaging and Vision, 29(1): pages 1-20, September 2007. Keywords : Gap closure, Higher-order, Active contour, Shape, Prior, Road network. @ARTICLE{Rochery07, author = {Rochery, M. and Jermyn, I. H. and Zerubia, J.}, title = {Higher-Order Active Contour Energies for Gap Closure}, year = {2007}, month = {September}, journal = {Journal of Mathematical Imaging and Vision}, volume = {29}, number = {1}, pages = {1-20}, url = {http://dx.doi.org/10.1007/s10851-007-0021-x}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2007_Rochery07.pdf}, keyword = {Gap closure, Higher-order, Active contour, Shape, Prior, Road network} } Abstract : One of the main difficulties in extracting line networks from images, and in particular road networks from remote sensing images, is the existence of interruptions in the data caused, for example, by occlusions. These can lead to gaps in the extracted network that do not correspond to gaps in the real network. In this paper, we describe a higher-order active contour energy that in addition to favouring network-like regions, includes a prior term penalizing networks containing ‘nearby opposing extremities’, thereby making gaps in the extracted network less likely. The new energy term causes such extremities to attract one another during gradient descent. They thus move towards one another and join, closing the gap. To minimize the energy, we develop specific techniques to handle the high-order derivatives that appear in the gradient descent equation. We present the results of automatic extraction of networks from real remote-sensing images, showing the ability of the model to overcome interruptions.

3 - Higher Order Active Contours. M. Rochery and I. H. Jermyn and J. Zerubia. International Journal of Computer Vision, 69(1): pages 27--42, August 2006. Keywords : Active contour, Shape, Higher-order, Prior, Road network. @ARTICLE{mr_ijcv_06, author = {Rochery, M. and Jermyn, I. H. and Zerubia, J.}, title = {Higher Order Active Contours}, year = {2006}, month = {August}, journal = {International Journal of Computer Vision}, volume = {69}, number = {1}, pages = {27--42}, url = {http://dx.doi.org/10.1007/s11263-006-6851-y}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2006_mr_ijcv_06.pdf}, keyword = {Active contour, Shape, Higher-order, Prior, Road network} } Abstract : We introduce a new class of active contour models that hold great promise for region and shape modelling, and we apply a special case of these models to the extraction of road networks from satellite and aerial imagery. The new models are arbitrary polynomial functionals on the space of boundaries, and thus greatly generalize the linear functionals used in classical contour energies. While classical energies are expressed as single integrals over the contour, the new energies incorporate multiple integrals, and thus describe long-range interactions between different sets of contour points. As prior terms, they describe families of contours that share complex geometric properties, without making reference to any particular shape, and they require no pose estimation. As likelihood terms, they can describe multi-point interactions between the contour and the data. To optimize the energies, we use a level set approach. The forces derived from the new energies are non-local however, thus necessitating an extension of standard level set methods. Networks are a shape family of great importance in a number of applications, including remote sensing imagery. To model them, we make a particular choice of prior quadratic energy that describes reticulated structures, and augment it with a likelihood term that couples the data at pairs of contour points to their joint geometry. Promising experimental results are shown on real images.

top of the page

3 PhD Thesis and Habilitations

1 - New higher-order active contour models, shape priors, and multiscale analysis: their application to road network extraction from very high resolution satellite images. T. Peng. PhD Thesis, Universite de Nice Sophia Antipolis, November 2008. Keywords : Higher-order active contour, Phase Field, Prior, Multiresolution, Road network, Very high resolution. Copyright : @PHDTHESIS{Peng08d, author = {Peng, T.}, title = {New higher-order active contour models, shape priors, and multiscale analysis: their application to road network extraction from very high resolution satellite images}, year = {2008}, month = {November}, school = {Universite de Nice Sophia Antipolis}, pdf = {http://tel.archives-ouvertes.fr/tel-00349768/fr/}, keyword = {Higher-order active contour, Phase Field, Prior, Multiresolution, Road network, Very high resolution} } Résumé : L'objectif de cette thèse est de développer et de valider des approches robustes d'extraction semi-automatique de réseaux routiers en zone urbaine dense à partir d'images satellitaires optiques à très haute résolution (THR). Nos modèles sont fondés sur une modélisation par champs de phase des contours actifs d'ordre supérieur (CAOS). Le probléme est difficile pour deux raisons principales : les images THR sont intrinsèquement complexes, et certaines zones des réseaux peuvent prendre une topologie arbitraire. Pour remédier à la complexité de l'information contenue dans les images THR, nous proposons une modélisation statistique multi-résolution des données ainsi qu'un modèle multi-résolution contraint a priori. Ces derniers permettent l'intégration des résultats de segmentation de résolution brute et de résolution fine. De plus, dans le cadre particulier de la mise à jour de réseaux routiers, nous présentons un modèle de forme a priori spécifique, dérivé d'une ancienne carte numérique issue d'un SIG. Ce terme spécifique a priori équilibre l'effet de la connaissance a priori générique apportée par le modèle de CAOS, qui décrit la forme géométrique générale des réseaux routiers. Cependant, le modèle classique de CAOS souffre d'une limitation importante : la largeur des branches du réseau est contrainte à d'être similaire au maximum du rayon de courbure des branches du réseau, fournissant ainsi un modèle non satisfaisant dans le cas de réseaux aux branches droites et étroites ou aux branches fortement incurvées et larges. Nous résolvons ce problème en proposant deux nouveaux modèles : l'un contenant un terme additionnel, nonlocal, non-linéaire de CAOS, et l'autre contenant un terme additionnel, nonlocal, linéaire de CAOS. Ces deux termes permettent le contrôle séparé de la largeur et de la courbure des branches, et fournissent une meilleure prolongation pour une même largeur. Le terme linéaire a plusieurs avantages : d'une part il se calcule plus efficacement, d'autre part il peut modéliser plusieurs largeurs de branche simultanément. Afin de remédier à la difficulté du choix des paramètres de ces modèles, nous analysons les conditions de stabilité pour une longue barre d'une largeur donnée décrite par ces énergies, et montrons ainsi comment choisir rigoureusement les paramètres des fonctions d'énergie. Des expériences sur des images satellitaires THR et la comparaison avec d'autres modèles démontrent la supériorité de nos modèles. Abstract : The objective of this thesis is to develop and validate robust approaches for the semi-automatic extraction of road networks in dense urban areas from very high resolution (VHR) optical satellite images. Our models are based on the recently developed higher-order active contour (HOAC) phase field framework. The problem is difficult for two main reasons: VHR images are intrinsically complex and network regions may have arbitrary topology. To tackle the complexity of the information contained in VHR images, we propose a multiresolution statistical data model and a multiresolution constrained prior model. They enable the integration of segmentation results from coarse resolution and fine resolution. Subsequently, for the particular case of road map updating, we present a specific shape prior model derived from an outdated GIS digital map. This specific prior term balances the effect of the generic prior knowledge carried by the HOAC model, which describes the geometric shape of road networks in general. However, the classical HOAC model suffers from a severe limitation: network branch width is constrained to be similar to maximum network branch radius of curvature, thereby providing a poor model of networks with straight narrow branches or highly curved, wide branches. We solve this problem by introducing two new models: one with an additional nonlinear nonlocal HOAC term, and one with an additional linear nonlocal HOAC term. Both terms allow separate control of branch width and branch curvature, and furnish better prolongation for the same width, but the linear term has several advantages: it is more efficient from a computational standpoint, and it is able to model multiple widths simultaneously. To cope with the difficulty of parameter selection of these models, we analyze the stability conditions for a long bar with a given width described by these energies, and hence show how to choose rigorously the parameters of the energy functions. Experiments on VHR satellite images and comparisons with other approaches demonstrate the superiority of our models.

2 - Contours actifs d'ordre supérieur et leur application à la détection de linéiques dans des images de télédétection. M. Rochery. PhD Thesis, Universite de Nice Sophia Antipolis, Sophia Antipolis, September 2005. Keywords : Active contour, Higher-order, Phase Field, Line networks, Road network. @PHDTHESIS{rochery_these, author = {Rochery, M.}, title = {Contours actifs d'ordre supérieur et leur application à la détection de linéiques dans des images de télédétection}, year = {2005}, month = {September}, school = {Universite de Nice Sophia Antipolis}, address = {Sophia Antipolis}, pdf = {http://hal.inria.fr/docs/00/04/86/28/PDF/tel-00010631.pdf}, keyword = {Active contour, Higher-order, Phase Field, Line networks, Road network} }

3 - 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}, url = {http://www.inria.fr/rrrt/tu-0663.html}, ps = {ftp://ftp.inria.fr/INRIA/publication/Theses/TU-0663.ps.gz}, 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

9 Conference articles

1 - An extended phase field higher-order active contour model for networks and its application to road network extraction from VHR satellite images. T. Peng and I. H. Jermyn and V. Prinet and J. Zerubia. In Proc. European Conference on Computer Vision (ECCV), Marseille, France, October 2008. Keywords : Dense urban area, Phase Field, Road network, Variational methods, Very high resolution. Copyright : @INPROCEEDINGS{Peng08c, author = {Peng, T. and Jermyn, I. H. and Prinet, V. and Zerubia, J.}, title = {An extended phase field higher-order active contour model for networks and its application to road network extraction from VHR satellite images}, year = {2008}, month = {October}, booktitle = {Proc. European Conference on Computer Vision (ECCV)}, address = {Marseille, France}, pdf = {http://kepler.ia.ac.cn/publications/pub/2008/Peng-ECCV08.pdf}, keyword = {Dense urban area, Phase Field, Road network, Variational methods, Very high resolution} } Abstract : This paper addresses the segmentation from an image of entities that have the form of a 'network', i.e. the region in the image corresponding to the entity is composed of branches joining together at junctions, e.g. road or vascular networks. We present a new phase field higher-order active contour (HOAC) prior model for network regions, and apply it to the segmentation of road networks from very high resolution satellite images. This is a hard problem for two reasons. First, the images are complex, with much 'noise' in the road region due to cars, road markings, etc., while the background is very varied, containing many features that are locally similar to roads. Second, network regions are complex to model, because they may have arbitrary topology. In particular, we address a severe limitation of a previous model in which network branch width was constrained to be similar to maximum network branch radius of curvature, thereby providing a poor model of networks with straight narrow branches or highly curved, wide branches. To solve this problem, we propose a new HOAC prior energy term, and reformulate it as a nonlocal phase field energy. We analyse the stability of the new model, and find that in addition to solving the above problem by separating the interactions between points on the same and opposite sides of a network branch, the new model permits the modelling of two widths simultaneously. The analysis also fixes some of the model parameters in terms of network width(s). After adding a likelihood energy, we use the model to extract the road network quasi-automatically from pieces of a QuickBird image, and compare the results to other models in the literature. The results demonstrate the superiority of the new model, the importance of strong prior knowledge in general, and of the new term in particular.

2 - Extraction of main and secondary roads in VHR images using a higher-order phase field model. T. Peng and I. H. Jermyn and V. Prinet and J. Zerubia. In Proc. XXI ISPRS Congress, Part A, Beijing, China, July 2008. Keywords : Road network, Urban areas, Satellite images, Segmentation, Modelling, Variational methods. Copyright : ISPRS @INPROCEEDINGS{Peng08a, author = {Peng, T. and Jermyn, I. H. and Prinet, V. and Zerubia, J.}, title = {Extraction of main and secondary roads in VHR images using a higher-order phase field model}, year = {2008}, month = {July}, booktitle = {Proc. XXI ISPRS Congress, Part A}, address = {Beijing, China}, keyword = {Road network, Urban areas, Satellite images, Segmentation, Modelling, Variational methods} } Abstract : This paper addresses the issue of extracting main and secondary road networks in dense urban areas from very high resolution (VHR, ~0.61m) satellite images. The difficulty with secondary roads lies in the low discriminative power of the grey-level distributions of road regions and the background, and the greater effect of occlusions and other noise on narrower roads. To tackle this problem, we use a previously developed higher-order active contour (HOAC) phase field model and augment it with an additional non-linear nonlocal term. The additional term allows separate control of road width and road curvature; thus more precise prior knowledge can be incorporated, and better road prolongation can be achieved for the same width. Promising results on QuickBird panchromatic images at reduced resolutions and comparisons with other models demonstrate the role and the efficiency of our new model.

3 - A Phase Field Model Incorporating Generic and Specific Prior Knowledge Applied to Road Network Extraction from VHR Satellite Images. T. Peng and I. H. Jermyn and V. Prinet and J. Zerubia and B. Hu. In Proc. British Machine Vision Conference (BMVC), Warwick, UK, September 2007. Keywords : Road network, Very high resolution, Higher-order, Active contour, Shape, Prior. @INPROCEEDINGS{Peng07a, author = {Peng, T. and Jermyn, I. H. and Prinet, V. and Zerubia, J. and Hu, B.}, title = {A Phase Field Model Incorporating Generic and Specific Prior Knowledge Applied to Road Network Extraction from VHR Satellite Images}, year = {2007}, month = {September}, booktitle = {Proc. British Machine Vision Conference (BMVC)}, address = {Warwick, UK}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2007_Peng07a.pdf}, keyword = {Road network, Very high resolution, Higher-order, Active contour, Shape, Prior} } Abstract : We address the problem of updating road maps in dense urban areas by extracting the main road network from a very high resolution (VHR) satellite image. Our model of the region occupied by the road network in the image is innovative. It incorporates three different types of prior geometric knowledge: generic boundary smoothness constraints, equivalent to a standard active contour prior; knowledge of the geometric properties of road networks (i.e. that they occupy regions composed of long, low-curvature segments joined at junctions), equivalent to a higher-order active contour prior; and knowledge of the road network at an earlier date derived from GIS data, similar to other ‘shape priors’ in the literature. In addition, we represent the road network region as a ‘phase field’, which offers a number of important advantages over other region modelling frameworks. All three types of prior knowledge prove important for overcoming the complexity of geometric ‘noise’ in VHR images. Promising results and a comparison with several other techniques demonstrate the effectiveness of our approach.

4 - Indexing Satellite Images with Features Computed from Man-Made Structures on the Earth’s Surface. A. Bhattacharya and M. Roux and H. Maitre and I. H. Jermyn and X. Descombes and J. Zerubia. In Proc. International Workshop on Content-Based Multimedia Indexing, Bordeaux, France, June 2007. Keywords : Indexation, Road network, Semantic, Retrieval, Feature statistics. @INPROCEEDINGS{Bhattacharya07a, author = {Bhattacharya, A. and Roux, M. and Maitre, H. and Jermyn, I. H. and Descombes, X. and Zerubia, J.}, title = {Indexing Satellite Images with Features Computed from Man-Made Structures on the Earth’s Surface}, year = {2007}, month = {June}, booktitle = {Proc. International Workshop on Content-Based Multimedia Indexing}, address = {Bordeaux, France}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2007_Bhattacharya07a.pdf}, keyword = {Indexation, Road network, Semantic, Retrieval, Feature statistics} } Abstract : Indexing and retrieval from remote sensing image databases relies on the extraction of appropriate information from the data about the entity of interest (e.g. land cover type) and on the robustness of this extraction to nuisance variables. Other entities in an image may be strongly correlated with the entity of interest and their properties can therefore be used to characterize this entity. The road network contained in an image is one example. The properties of road networks vary considerably from one geographical environment to another, and they can therefore be used to classify and retrieve such environments. In this paper, we define several such environments, and classify them with the aid of geometrical and topological features computed from the road networks occurring in them. The relative failure of network extraction methods in certain types of urban area obliges us to segment such areas and to add a second set of geometrical and topological features computed from the segmentations. To validate the approach, feature selection and SVM linear kernel classification are performed on the feature set arising from a diverse image database.

top of the page

navigation : 1 - 2 - 3 display : 10 per page | 20 per page | 50 per page

These pages were generated by