Publications de Giuseppe Scarpa

Résultat de la recherche dans la liste des publications :

• 2 Articles
• 6 Articles de conférence
• 2 Rapports de recherche et Rapports techniques

nouvelle recherche | bibtex

affichage : 10 par page | 20 par page | 50 par page

2 Articles

1 - Hierarchical Multiple Markov Chain Model for Unsupervised Texture Segmentation. G. Scarpa et R. Gaetano et M. Haindl et J. Zerubia. IEEE Trans. on Image Processing, 18(8): pages 1830-1843, août 2009. Mots-clés : Hierarchical Image Models, Markov Process, Pattern Analysis. @ARTICLE{ScarpaTIP09, author = {Scarpa, G. and Gaetano, R. and Haindl, M. and Zerubia, J.}, title = { Hierarchical Multiple Markov Chain Model for Unsupervised Texture Segmentation}, year = {2009}, month = {août}, journal = {IEEE Trans. on Image Processing}, volume = {18}, number = {8}, pages = {1830-1843}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=5161445&arnumber=4914796&count=21&index=11}, keyword = {Hierarchical Image Models, Markov Process, Pattern Analysis} } Abstract : In this paper, we present a novel multiscale texture model and a related algorithm for the unsupervised segmentation of color images. Elementary textures are characterized by their spatial interactions with neighboring regions along selected directions. Such interactions are modeled, in turn, by means of a set of Markov chains, one for each direction, whose parameters are collected in a feature vector that synthetically describes the texture. Based on the feature vectors, the texture are then recursively merged, giving rise to larger and more complex textures, which appear at different scales of observation: accordingly, the model is named Hierarchical Multiple Markov Chain (H-MMC). The Texture Fragmentation and Reconstruction (TFR) algorithm, addresses the unsupervised segmentation problem based on the H-MMC model. The “fragmentation” step allows one to find the elementary textures of the model, while the “reconstruction” step defines the hierarchical image segmentation based on a probabilistic measure (texture score) which takes into account both region scale and inter-region interactions. The performance of the proposed method was assessed through the Prague segmentation benchmark, based on mosaics of real natural textures, and also tested on real-world natural and remote sensing images.

2 - Supervised Segmentation of Remote Sensing Images Based on a Tree-Structure MRF Model. G. Poggi et G. Scarpa et J. Zerubia. IEEE Trans. Geoscience and Remote Sensing, 43(8): pages 1901-1911, août 2005. Mots-clés : Classification, Segmentation, Champs de Markov. @ARTICLE{ieeetgrs_05, author = {Poggi, G. and Scarpa, G. and Zerubia, J.}, title = {Supervised Segmentation of Remote Sensing Images Based on a Tree-Structure MRF Model}, year = {2005}, month = {août}, journal = {IEEE Trans. Geoscience and Remote Sensing}, volume = {43}, number = {8}, pages = {1901-1911}, pdf = {http://ieeexplore.ieee.org/iel5/36/32001/01487647.pdf?tp=&arnumber=1487647&isnumber=32001}, keyword = {Classification, Segmentation, Champs de Markov} }

haut de la page

6 Articles de conférence

1 - Morphological road segmentation in urban areas from high resolution satellite images. R. Gaetano et J. Zerubia et G. Scarpa et G. Poggi. Dans International Conference on Digital Signal Processing, Corfu, Greece, juillet 2011. Mots-clés : Segmentation, Classification, skeletonization , pattern recognition, shape analysis. @INPROCEEDINGS{GaetanoDSP, author = {Gaetano, R. and Zerubia, J. and Scarpa, G. and Poggi, G.}, title = {Morphological road segmentation in urban areas from high resolution satellite images}, year = {2011}, month = {juillet}, booktitle = {International Conference on Digital Signal Processing}, address = {Corfu, Greece}, url = {http://hal.inria.fr/inria-00618222/fr/}, keyword = {Segmentation, Classification, skeletonization , pattern recognition, shape analysis} } Abstract : High resolution satellite images provided by the last generation sensors significantly increased the potential of almost all the image information mining (IIM) applications related to earth observation. This is especially true for the extraction of road information, task of primary interest for many remote sensing applications, which scope is more and more extended to complex urban scenarios thanks to the availability of highly detailed images. This context is particularly challenging due to such factors as the variability of road visual appearence and the occlusions from entities like trees, cars and shadows. On the other hand, the peculiar geometry and morphology of man-made structures, particularly relevant in urban areas, is enhanced in high resolution images, making this kind of information especially useful for road detection. In this work, we provide a new insight on the use of morphological image analysis for road extraction in complex urban scenarios, and propose a technique for road segmentation that only relies on this domain. The keypoint of the technique is the use of skeletons as powerful descriptors for road objects: the proposed method is based on an ad-hoc skeletonization procedure that enhances the linear structure of road segments, and extracts road objects by first detecting their skeletons and then associating each of them with a region of the image. Experimental results are presented on two different high resolution satellite images of urban areas.

2 - Graph-based Analysis of Textured Images for Hierarchical Segmentation. R. Gaetano et G. Scarpa et T. Sziranyi. Dans Proc. British Machine Vision Conference (BMVC), Aberystwyth, UK, août 2010. @INPROCEEDINGS{Gaetano2010, author = {Gaetano, R. and Scarpa, G. and Sziranyi, T.}, title = {Graph-based Analysis of Textured Images for Hierarchical Segmentation}, year = {2010}, month = {août}, booktitle = {Proc. British Machine Vision Conference (BMVC)}, address = {Aberystwyth, UK}, url = {http://hal.archives-ouvertes.fr/inria-00506596}, keyword = {} } Abstract : The Texture Fragmentation and Reconstruction (TFR) algorithm has beenrecently introduced to address the problem of image segmentationby textural properties, based on a suitable image description toolknown as the Hierarchical Multiple Markov Chain (H-MMC) model. TFRprovides a hierarchical set of nested segmentation maps by firstidentifying the elementary image patterns, and then merging themsequentially to identify complete textures at different scales ofobservation.In this work, we propose a major modification to the TFR by resortingto a graph based description of the image content and a graph clusteringtechnique for the enhancement and extraction of image patterns. Aprocedure based on mathematical morphology will be introduced thatallows for the construction of a color-wise image representationby means of multiple graph structures, along with a simple clusteringtechnique aimed at cutting the graphs and correspondingly segmentgroups of connected components with a similar spatial context.The performance assessment, realized both on synthetic compositionsof real-world textures and images from the remote sensing domain,confirm the effectiveness and potential of the proposed method.

3 - Unsupervised Hierarchical Image Segmentation based on the TS-MRF model and Fast Mean-Shift Clustering. R. Gaetano et G. Scarpa et G. Poggi et J. Zerubia. Dans Proc. European Signal Processing Conference (EUSIPCO), Lausanne, Switzerland, août 2008. Mots-clés : Segmentation, Markov Random Fields, Mean Shift, Land Classification. @INPROCEEDINGS{Gaetano2008, author = {Gaetano, R. and Scarpa, G. and Poggi, G. and Zerubia, J.}, title = {Unsupervised Hierarchical Image Segmentation based on the TS-MRF model and Fast Mean-Shift Clustering}, year = {2008}, month = {août}, booktitle = {Proc. European Signal Processing Conference (EUSIPCO)}, address = {Lausanne, Switzerland}, pdf = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7080521}, keyword = {Segmentation, Markov Random Fields, Mean Shift, Land Classification} } Abstract : Tree-Structured Markov Random Field (TS-MRF) models have been recently proposed to provide a hierarchical multiscale description of images. Based on such a model, the unsupervised image segmentation is carried out by means of a sequence of nested class splits, where each class is modeled as a local binary MRF. We propose here a new TS-MRF unsupervised segmentation technique which improves upon the original algorithm by selecting a better tree structure and eliminating spurious classes. Such results are obtained by using the Mean-Shift procedure to estimate the number of pdf modes at each node (thus allowing for a non-binary tree), and to obtain a more reliable initial clustering for subsequent MRF optimization. To this end, we devise a new reliable and fast clustering algorithm based on the Mean-Shift technique. Experimental results prove the potential of the proposed method.

4 - A Hierarchical Texture Model for Unsupervised Segmentation of Remotely Sensed Images. G. Scarpa et M. Haindl et J. Zerubia. Dans Scandinavian Conference on Image Analysis, Vol. 4522/2007, pages 303-312, series LNCS 4522, Ed. Springer Berlin / Heidelberg, Aalborg, Denmark, juin 2007. @INPROCEEDINGS{scarpa_scia_07, author = {Scarpa, G. and Haindl, M. and Zerubia, J.}, title = {A Hierarchical Texture Model for Unsupervised Segmentation of Remotely Sensed Images}, year = {2007}, month = {juin}, booktitle = {Scandinavian Conference on Image Analysis}, volume = {4522/2007}, pages = {303-312}, series = {LNCS 4522}, editor = {Springer Berlin / Heidelberg}, address = {Aalborg, Denmark}, url = {http://link.springer.com/chapter/10.1007%2F978-3-540-73040-8_31}, keyword = {} }

5 - A Hierarchical finite-state model for texture segmentation. G. Scarpa et M. Haindl et J. Zerubia. Dans Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vol. 1, pages 1209-1212, Honolulu, HI (USA), avril 2007. @INPROCEEDINGS{scarpa_icassp_07, author = {Scarpa, G. and Haindl, M. and Zerubia, J.}, title = {A Hierarchical finite-state model for texture segmentation}, year = {2007}, month = {avril}, booktitle = {Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, volume = {1}, pages = {1209-1212}, address = {Honolulu, HI (USA)}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4217303}, keyword = {} }

6 - Segmentation of remote sensing images by supervised TS-MRF. G. Poggi et G. Scarpa et J. Zerubia. Dans Proc. IEEE International Conference on Image Processing (ICIP), Singapore, octobre 2004. @INPROCEEDINGS{poggi_icip04, author = {Poggi, G. and Scarpa, G. and Zerubia, J.}, title = {Segmentation of remote sensing images by supervised TS-MRF}, year = {2004}, month = {octobre}, booktitle = {Proc. IEEE International Conference on Image Processing (ICIP)}, address = {Singapore}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1421441}, keyword = {} }

haut de la page

2 Rapports de recherche et Rapports techniques

1 - Hierarchical finite-state modeling for texture segmentation with application to forest classification. G. Scarpa et M. Haindl et J. Zerubia. Research Report 6066, INRIA, INRIA, France, décembre 2006. Mots-clés : Texture, Segmentation, Co-occurrence matrix, Approche structurelle, MCMC, Synthesis. @TECHREPORT{scarparr06, author = {Scarpa, G. and Haindl, M. and Zerubia, J.}, title = {Hierarchical finite-state modeling for texture segmentation with application to forest classification}, year = {2006}, month = {décembre}, institution = {INRIA}, type = {Research Report}, number = {6066}, address = {INRIA, France}, url = {https://hal.inria.fr/inria-00118420}, keyword = {Texture, Segmentation, Co-occurrence matrix, Approche structurelle, MCMC, Synthesis} } Abstract : In this research report we present a new model for texture representation which is particularly well suited for image analysis and segmentation. Any image is first discretized and then a hierarchical finite-state region-based model is automatically coupled with the data by means of a sequential optimization scheme, namely the Texture Fragmentation and Reconstruction (TFR) algorithm. The TFR algorithm allows to model both intra- and inter-texture interactions, and eventually addresses the segmentation task in a completely unsupervised manner. Moreover, it provides a hierarchical output, as the user may decide the scale at which the segmentation has to be given. Tests were carried out on both natural texture mosaics provided by the Prague Texture Segmentation Datagenerator Benchmark and remote-sensing data of forest areas provided by the French National Forest Inventory (IFN).

2 - A Binary Tree-Structured MRF Model for Multispectral Satellite Image Segmentation. G. Scarpa et G. Poggi et J. Zerubia. Rapport de Recherche 5062, INRIA, France, décembre 2003. Mots-clés : Estimation bayesienne, Classification, Champs de Markov, Modeles hierarchiques. @TECHREPORT{Scarpa03, author = {Scarpa, G. and Poggi, G. and Zerubia, J.}, title = {A Binary Tree-Structured MRF Model for Multispectral Satellite Image Segmentation}, year = {2003}, month = {décembre}, institution = {INRIA}, type = {Research Report}, number = {5062}, address = {France}, url = {https://hal.inria.fr/inria-00071522}, pdf = {https://hal.inria.fr/file/index/docid/71522/filename/RR-5062.pdf}, ps = {https://hal.inria.fr/docs/00/07/15/22/PS/RR-5062.ps}, keyword = {Estimation bayesienne, Classification, Champs de Markov, Modeles hierarchiques} } Résumé : Dans ce rapport, nous proposons un modèle markovien a priori structuré à arbre binaire (le TS-MRF) pour la segmentation d'images satellitaires multispectrales. Ce modèle permet de représenter un champ bidimensionnel par une séquence de champs de Markov binaires, chacun correspondant à un noeud de l'arbre. Pour avoir une bonne classification, on peut adapter le modèle TS-MRF à la structure intrinsèque des données, en définissant un MRF, à plusieurs paramètres, très flexible. Bien que l'on définisse le modèle global sur tout l'arbre, l'optimisation et l'estimation peuvent être poursuivis en considérant un noeud à la fois, à partir de la racine jusqu'aux feuilles, avec une réduction significative de la complexité. En effet, on a montré expérimentalement que l'algorithme global est beaucoup plus rapide qu'un algorithme conventionnel fondé sur le modèle markovien d'Ising, en particulier quand le nombre des bandes spectrales est très grand. Grâce à la procédure d'optimisation séquentielle, ce modèle permet aussi de déterminer le nombre des classes présentes dans l'image satellitaire, dans le cadre d'une classification non supervisée, à travers une condition d'arrêt définie localement pour chaque noeud. Nous avons effectué des expériences sur une image SPOT de la baie de Lannion, pour laquelle nous disposons d'une vérité terrain, et nous avons trouvé que le modèle proposé fournit de meilleurs résultats que certains autres modèles de Markov et que d'autres méthodes variationnelles. Abstract : In this work we detail a tree-structured MRF (TS-MRF) prior model useful for segmentation of multispectral satellite images. This model allows a hierarchical representation of a 2-D field by the use of a sequence of binary MRFs, each corresponding to a node in the tree. In order to get good performances, one can fit the intrinsic structure of the data to the TS-MRF model, thereby defining a multi-parameter, flexible, MRF. Although a global MRF model is defined on the whole tree, optimization as well estimation can be carried out by working on a single node at a time, from the root down to the leaves, with a significant reduction in complexity. Indeed the overall algorithm is proved experimentally to be much faster than a comparable algorithm based on a conventional Ising MRF model, especially when the number of bands becomes very large. Thanks to the sequential optimization procedure, this model also addresses the cluster validation problem of unsupervised segmentation, through the use of a stopping condition local to each node. Experiments on a SPOT image of the Lannion Bay, a ground-truth of which is available, prove the superior performance of the algorithm w.r.t. some other MRF based algorithms for supervised segmentation, as well as w.r.t. some variational methods.

haut de la page

affichage : 10 par page | 20 par page | 50 par page

Ces pages sont générées par