Marie Rochery

Ancien Doctorant, MESR / UNSA

Contact :

Résumé :

Mini CV :

Enseignement :

Dernières publications dans le projet Ariana :

Higher-Order Active Contour Energies for Gap Closure. M. Rochery et I. H. Jermyn et J. Zerubia. Journal of Mathematical Imaging and Vision, 29(1): pages 1-20, septembre 2007. Mots-clés : Gap closure, Ordre superieur, Contour actif, Forme, A priori, Reseaux routiers. @ARTICLE{Rochery07, author = {Rochery, M. and Jermyn, I. H. and Zerubia, J.}, title = {Higher-Order Active Contour Energies for Gap Closure}, year = {2007}, month = {septembre}, 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, Ordre superieur, Contour actif, Forme, A priori, Reseaux routiers} } 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. Higher Order Active Contours. M. Rochery et I. H. Jermyn et J. Zerubia. International Journal of Computer Vision, 69(1): pages 27--42, août 2006. Mots-clés : Contour actif, Forme, Ordre superieur, A priori, Reseaux routiers. @ARTICLE{mr_ijcv_06, author = {Rochery, M. and Jermyn, I. H. and Zerubia, J.}, title = {Higher Order Active Contours}, year = {2006}, month = {août}, 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 = {Contour actif, Forme, Ordre superieur, A priori, Reseaux routiers} } 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. Higher-Order Active Contour Energies for Gap Closure. M. Rochery et I. H. Jermyn et J. Zerubia. Rapport de Recherche 5717, INRIA, France, octobre 2005. Mots-clés : Reseaux routiers, Continuity, Gap closure, Ordre superieur, Contour actif, Forme. @TECHREPORT{RR_5717, author = {Rochery, M. and Jermyn, I. H. and Zerubia, J.}, title = {Higher-Order Active Contour Energies for Gap Closure}, year = {2005}, month = {octobre}, institution = {INRIA}, type = {Research Report}, number = {5717}, address = {France}, url = {http://hal.inria.fr/inria-00070300/fr/}, pdf = {https://hal.inria.fr/file/index/docid/70300/filename/RR-5717.pdf}, ps = {http://hal.inria.fr/docs/00/07/03/00/PS/RR-5717.ps}, keyword = {Reseaux routiers, Continuity, Gap closure, Ordre superieur, Contour actif, Forme} } Résumé : L'un des principaux problèmes lors de l'extraction de réseaux linéiques dans des images, et en particulier l'extraction de réseaux routiers dans des images de télédétection, est l'existence d'interruptions dans les données, causées, par exemple, par des occultations. Ces interruptions peuvent mener à des trous dans le réseau extrait qui n'existent pas dans le réseau réel. Dans ce rapport, nous décrivons une énergie de contour actif d'ordre supérieur qui, en plus de favoriser les régions composées de bras fins et connectés entre eux, inclut un terme d'a priori qui pénalise les configurations du réseau où des extremités proches et se faisant face apparaissent. L'apparition dans le réseau extrait de ces configurations est donc moins probable. Si des extremités proches et se faisant face apparaissent pendant l'évolution par descente de gradient utilisée pour minimiser l'énergie, le nouveau terme dans l'énergie crée une attraction entre ces extremités, qui se rapprochent donc l'une de l'autre et se rejoignent, fermant ainsi le trou entre elles. Pour minimiser l'énergie, nous développons des techniques spécifiques pour traiter les derivées d'ordre élevé qui apparaissent dans l'équation de descente de gradient. Nous présentons des résultats d'extraction automatique de réseaux routiers à partir d'images de télédétection, montrant ainsi la capacité du modèle à surmonter les interruptions. 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 report, we describe a higher-order active contour energy that in addition to favouring network-like regions composed of thin arms joining at junctions, also includes a prior term that penalizes network configurations containing `nearby opposing extremities', and thereby makes their appearance in the extracted network less likely. If nearby opposing extremities form during the gradient descent evolution used to minimize the energy, the new energy term causes the extremities to attract one another, and hence to move towards one another and join, thus 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.

Liste complète des publications dans le projet Ariana