Publications of Florent Lafarge

Result of the query in the list of publications :

• 8 Articles
• 1 PhD Thesis and Habilitation
• 18 Conference articles
• 5 Technical and Research Reports

new search | get the bibtex

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

8 Articles

1 - A Marked Point Process for Modeling Lidar Waveforms. C. Mallet and F. Lafarge and M. Roux and U. Soergel and F. Bretar and C. Heipke. IEEE Trans. Image Processing, 19(12): pages 3204-3221, December 2010. Keywords : Clustering algorithms, Image color analysis, Image edge detection, Image segmentation, Monte Carlo Sampling, Object-based stochastic model. @ARTICLE{mallet_tip2010, author = {Mallet, C. and Lafarge, F. and Roux, M. and Soergel, U. and Bretar, F. and Heipke, C.}, title = {A Marked Point Process for Modeling Lidar Waveforms}, year = {2010}, month = {December}, journal = {IEEE Trans. Image Processing}, volume = {19}, number = {12}, pages = {3204-3221}, url = {http://dx.doi.org/10.1109/TIP.2010.2052825}, keyword = {Clustering algorithms, Image color analysis, Image edge detection, Image segmentation, Monte Carlo Sampling, Object-based stochastic model} } Abstract : Lidar waveforms are 1D signals representing a train of echoes caused by reflections at different targets. Modeling these echoes with the appropriate parametric function is useful to retrieve information about the physical characteristics of the targets. This paper presents a new probabilistic model based on a marked point process which reconstructs the echoes from recorded discrete waveforms as a sequence of parametric curves. Such an approach allows to fit each mode of a waveform with the most suitable function and to deal with both, symmetric and asymmetric, echoes. The model takes into account a data term, which measures the coherence between the models and the waveforms, and a regularization term, which introduces prior knowledge on the reconstructed signal. The exploration of the associated configuration space is performed by a Reversible Jump Markov Chain Monte Carlo sampler coupled with simulated annealing. Experiments with different kinds of lidar signals, especially from urban scenes, show the high potential of the proposed approach. To further demonstrate the advantages of the suggested method, actual laser scans are classified and the results are reported.

2 - Geometric Feature Extraction by a Multi-Marked Point Process . F. Lafarge and G. Gimel'farb and X. Descombes. IEEE Trans. Pattern Analysis and Machine Intelligence, 32(9): pages 1597-1609, September 2010. Keywords : Shape extraction, Spatial point process, Stochastic geometry, fast optimization, Texture, remote sensing. @ARTICLE{pami09b_lafarge, author = {Lafarge, F. and Gimel'farb, G. and Descombes, X.}, title = {Geometric Feature Extraction by a Multi-Marked Point Process }, year = {2010}, month = {September}, journal = {IEEE Trans. Pattern Analysis and Machine Intelligence}, volume = {32}, number = {9}, pages = {1597-1609}, url = {http://dx.doi.org/10.1109/TPAMI.2009.152}, keyword = {Shape extraction, Spatial point process, Stochastic geometry, fast optimization, Texture, remote sensing} } Abstract : This paper presents a new stochastic marked point process for describing images in terms of a finite library of geometric objects. Image analysis based on conventional marked point processes has already produced convincing results but at the expense of parameter tuning, computing time, and model specificity. Our more general multimarked point process has simpler parametric setting, yields notably shorter computing times, and can be applied to a variety of applications. Both linear and areal primitives extracted from a library of geometric objects are matched to a given image using a probabilistic Gibbs model, and a Jump-Diffusion process is performed to search for the optimal object configuration. Experiments with remotely sensed images and natural textures show that the proposed approach has good potential. We conclude with a discussion about the insertion of more complex object interactions in the model by studying the compromise between model complexity and efficiency.

3 - Insertion of 3D-primitives in mesh-based representations: Towards compact models preserving the details. F. Lafarge and R. Keriven and M. Brédif. IEEE Trans. Image Processing, 19(7): pages 1683-1694, July 2010. Keywords : 3-D reconstruction, Graph-cut , Shape extraction, urban scenes. @ARTICLE{lafarge_tip2010, author = {Lafarge, F. and Keriven, R. and Brédif, M.}, title = {Insertion of 3D-primitives in mesh-based representations: Towards compact models preserving the details}, year = {2010}, month = {July}, journal = {IEEE Trans. Image Processing}, volume = {19}, number = {7}, pages = {1683-1694}, url = {http://dx.doi.org/10.1109/TIP.2010.2045695}, keyword = {3-D reconstruction, Graph-cut , Shape extraction, urban scenes} } Abstract : We propose an original hybrid modeling process of urban scenes that represents 3-D models as a combination of mesh-based surfaces and geometric 3-D-primitives. Meshes describe details such as ornaments and statues, whereas 3-D-primitives code for regular shapes such as walls and columns. Starting from an 3-D-surface obtained by multiview stereo techniques, these primitives are inserted into the surface after being detected. This strategy allows the introduction of semantic knowledge, the simplification of the modeling, and even correction of errors generated by the acquisition process. We design a hierarchical approach exploring different scales of an observed scene. Each level consists first in segmenting the surface using a multilabel energy model optimized by -expansion and then in fitting 3-D-primitives such as planes, cylinders or tori on the obtained partition where relevant. Experiments on real meshes, depth maps and synthetic surfaces show good potential for the proposed approach.

4 - Structural approach for building reconstruction from a single DSM. F. Lafarge and X. Descombes and J. Zerubia and M. Pierrot-Deseilligny. IEEE Trans. Pattern Analysis and Machine Intelligence, 32(1): pages 135-147, January 2010. @ARTICLE{lafarge_pami09, author = {Lafarge, F. and Descombes, X. and Zerubia, J. and Pierrot-Deseilligny, M.}, title = {Structural approach for building reconstruction from a single DSM}, year = {2010}, month = {January}, journal = {IEEE Trans. Pattern Analysis and Machine Intelligence}, volume = {32}, number = {1}, pages = {135-147}, url = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2008.281}, keyword = {} } Abstract : We present a new approach for building reconstruction from a single Digital Surface Model (DSM). It treats buildings as an assemblage of simple urban structures extracted from a library of 3D parametric blocks (like a LEGO set). First, the 2D-supports of the urban structures are extracted either interactively or automatically. Then, 3D-blocks are placed on the 2D-supports using a Gibbs model which controls both the block assemblage and the fitting to data. A Bayesian decision finds the optimal configuration of 3D--blocks using a Markov Chain Monte Carlo sampler associated with original proposition kernels. This method has been validated on multiple data set in a wide-resolution interval such as 0.7 m satellite and 0.1 m aerial DSMs, and provides 3D representations on complex buildings and dense urban areas with various levels of detail.

5 - Automatic Building Extraction from DEMs using an Object Approach and Application to the 3D-city Modeling. F. Lafarge and X. Descombes and J. Zerubia and M. Pierrot-Deseilligny. Journal of Photogrammetry and Remote Sensing, 63(3): pages 365-381, May 2008. Keywords : Building extraction, 3D reconstruction, Digital Elevation Model, Stochastic geometry. @ARTICLE{lafarge_jprs08, author = {Lafarge, F. and Descombes, X. and Zerubia, J. and Pierrot-Deseilligny, M.}, title = {Automatic Building Extraction from DEMs using an Object Approach and Application to the 3D-city Modeling}, year = {2008}, month = {May}, journal = {Journal of Photogrammetry and Remote Sensing}, volume = {63}, number = {3}, pages = {365-381}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2008_lafarge_jprs08.pdf}, keyword = {Building extraction, 3D reconstruction, Digital Elevation Model, Stochastic geometry} } Abstract : In this paper, we present an automatic building extraction method from Digital Elevation Models based on an object approach. First, a rough approximation of the building footprints is realized by a method based on marked point processes: the building footprints are modeled by rectangle layouts. Then, these rectangular footprints are regularized by improving the connection between the neighboring rectangles and detecting the roof height discontinuities. The obtained building footprints are structured footprints: each element represents a specific part of an urban structure. Results are finally applied to a 3D-city modeling process.

6 - Détection de feux de forêt par analyse statistique d'évènements rares à partir d'images infrarouges thermiques. F. Lafarge and X. Descombes and J. Zerubia and S. Mathieu. Traitement du Signal, 24(1), 2007. Note : copyright Traitement du Signal Keywords : Gaussian Field, Rare event, DT-caracteristic, Intensity peak. @ARTICLE{lafarge_ts06, author = {Lafarge, F. and Descombes, X. and Zerubia, J. and Mathieu, S.}, title = {Détection de feux de forêt par analyse statistique d'évènements rares à partir d'images infrarouges thermiques}, year = {2007}, journal = {Traitement du Signal}, volume = {24}, number = {1}, note = {copyright Traitement du Signal}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2007_lafarge_ts06.pdf}, keyword = {Gaussian Field, Rare event, DT-caracteristic, Intensity peak} }

7 - Automatic building 3D reconstruction from DEMs. F. Lafarge and X. Descombes and J. Zerubia and M. Pierrot-Deseilligny. Revue Française de Photogrammétrie et de Télédétection (SFPT), 184: pages 48--53, 2006. Keywords : 3D-reconstruction, Digital Elevation Model, Building extraction, dense urban areas. @ARTICLE{lafarge_sfpt06, author = {Lafarge, F. and Descombes, X. and Zerubia, J. and Pierrot-Deseilligny, M.}, title = {Automatic building 3D reconstruction from DEMs}, year = {2006}, journal = {Revue Française de Photogrammétrie et de Télédétection (SFPT)}, volume = {184}, pages = {48--53}, url = {http://isprs.free.fr/documents/Papers/T07-32.pdf}, keyword = {3D-reconstruction, Digital Elevation Model, Building extraction, dense urban areas} } Abstract : This paper is about an example of PLEIADES applications, the 3D building reconstruction. The future PLEIADES satellites are especially well adapted to deal with 3D building reconstruction through the sub-metric resolution of images and its stereoscopic characteristics. We propose a fully automatic 3D-city model of dense urban areas using a parametric approach. First, a Digital Elevation Model (DEM) is generated using an algorithm based on a maximum-flow formulation using three views. Then, building footprints are extracted from the DEM through an automatic method based on marked point processes : they are represented by an association of rectangles that we regularize by improving the connection of the neighboring rectangles and the facade discontinuity detection. Finally, a 3D-reconstruction method based on a skeleton process which allows to model the rooftops is proposed from the DEM and the building footprints. The different building heights constitute parameters which are estimated and then regularized by the ”K-means” algorithm including an entropy term.

8 - Modèle Paramétrique pour la Reconstruction Automatique en 3D de Zones Urbaines Denses à partir d'Images Satellitaires Haute Résolution. F. Lafarge and X. Descombes and J. Zerubia and M. Pierrot-Deseilligny. Revue Française de Photogrammétrie et de Télédétection (SFPT), 180: pages 4--12, 2005. Keywords : 3D reconstruction, Urban areas, Bayesian approach, MCMC, Satellite images. Copyright : SFPT @ARTICLE{lafarge_sfpt05, author = {Lafarge, F. and Descombes, X. and Zerubia, J. and Pierrot-Deseilligny, M.}, title = {Modèle Paramétrique pour la Reconstruction Automatique en 3D de Zones Urbaines Denses à partir d'Images Satellitaires Haute Résolution}, year = {2005}, journal = {Revue Française de Photogrammétrie et de Télédétection (SFPT)}, volume = {180}, pages = {4--12}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2005_lafarge_sfpt05.pdf}, keyword = {3D reconstruction, Urban areas, Bayesian approach, MCMC, Satellite images} }

top of the page

PhD Thesis and Habilitation

1 - Modèles stochastiques pour la reconstruction tridimensionnelle d'environnements urbains. F. Lafarge. PhD Thesis, Ecole des Mines de Paris, October 2007. Keywords : 3D reconstruction, Urban areas, Satellite images, Structural approach, Simulated Annealing, MCMC. @PHDTHESIS{lafarge_phd07, author = {Lafarge, F.}, title = {Modèles stochastiques pour la reconstruction tridimensionnelle d'environnements urbains}, year = {2007}, month = {October}, school = {Ecole des Mines de Paris}, url = {http://tel.archives-ouvertes.fr/tel-00179695/en/}, keyword = {3D reconstruction, Urban areas, Satellite images, Structural approach, Simulated Annealing, MCMC} } Résumé : Cette thèse aborde le problème de la reconstruction tridimensionnelle de zones urbaines à partir d'images satellitaires très haute résolution. Le contenu informatif de ce type de données est insuffisant pour permettre une utilisation efficace des nombreux algorithmes développés pour des données aériennes. Dans ce contexte, l'introduction de connaissances a priori fortes sur les zones urbaines est nécessaire. Les outils stochastiques sont particulièrement bien adaptés pour traiter cette problématique. Nous proposons une approche structurelle pour aborder ce sujet. Cela consiste à modéliser un bâtiment comme un assemblage de modules urbains élémentaires extraits d'une bibliothèque de modèles 3D paramétriques. Dans un premier temps, nous extrayons les supports 2D de ces modules à partir d'un Modèle Numérique d' Elévation (MNE). Le résultat est un agencement de quadrilatères dont les éléments voisins sont connectés entre eux. Ensuite, nous reconstruisons les bâtiments en recherchant la configuration optimale de modèles 3D se fixant sur les supports précédemment extraits. Cette configuration correspond à la réalisation qui maximise une densité mesurant la cohérence entre la réalisation et le MNE, mais également prenant en compte des connaissances a priori telles que des lois d'assemblage des modules. Nous discutons enfin de la pertinence de cette approche en analysant les résultats obtenus à partir de données satellitaires (simulations PLEIADES). Des expérimentations sont également réalisées à partir d'images aériennes mieux résolues.

top of the page

18 Conference articles

1 - Building large urban environments from unstructured point data. F. Lafarge and C. Mallet. In Proc. IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, November 2011. @INPROCEEDINGS{lafarge_iccv11, author = {Lafarge, F. and Mallet, C.}, title = {Building large urban environments from unstructured point data}, year = {2011}, month = {November}, booktitle = {Proc. IEEE International Conference on Computer Vision (ICCV)}, address = {Barcelona, Spain}, pdf = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6126353}, keyword = {} }

2 - Generating compact meshes under planar constraints: an automatic approach for modeling buildings lidar. Y. Verdié and F. Lafarge and J. Zerubia. In Proc. IEEE International Conference on Image Processing (ICIP), Brussels, Belgium, September 2011. Keywords : 3D-Modeling, shape analysis, Mesh processing. @INPROCEEDINGS{VerdieICIP11, author = {Verdié, Y. and Lafarge, F. and Zerubia, J.}, title = {Generating compact meshes under planar constraints: an automatic approach for modeling buildings lidar}, year = {2011}, month = {September}, booktitle = {Proc. IEEE International Conference on Image Processing (ICIP)}, address = {Brussels, Belgium}, url = {http://hal.inria.fr/inria-00605623/fr/}, keyword = {3D-Modeling, shape analysis, Mesh processing} } Abstract : We present an automatic approach for modeling buildings from aerial LiDAR data. The method produces accurate, watertight and compact meshes under planar constraints which are especially designed for urban scenes. The LiDAR point cloud is classified through a non-convex energy minimization problem in order to separate the points labeled as building. Roof structures are then extracted from this point subset, and used to control the meshing procedure. Experiments highlight the potential of our method in term of minimal rendering, accuracy and compactness

3 - Hybrid Multi-view Reconstruction by Jump-Diffusion. F. Lafarge and R. Keriven and M. Brédif and H. Vu. In Proc. IEEE Computer Vision and Pattern Recognition (CVPR), San Franscico, U.S., June 2010. @INPROCEEDINGS{lafarge_cvpr10, author = {Lafarge, F. and Keriven, R. and Brédif, M. and Vu, H.}, title = {Hybrid Multi-view Reconstruction by Jump-Diffusion}, year = {2010}, month = {June}, booktitle = {Proc. IEEE Computer Vision and Pattern Recognition (CVPR)}, address = {San Franscico, U.S.}, pdf = {http://certis.enpc.fr/publications/papers/CVPR10a.pdf}, keyword = {} }

4 - Combining meshes and geometric primitives for accurate and semantic modeling. F. Lafarge and R. Keriven and M. Brédif. In Proc. British Machine Vision Conference (BMVC), London, U.K., November 2009. @INPROCEEDINGS{lafarge_bmvc09, author = {Lafarge, F. and Keriven, R. and Brédif, M.}, title = {Combining meshes and geometric primitives for accurate and semantic modeling}, year = {2009}, month = {November}, booktitle = {Proc. British Machine Vision Conference (BMVC)}, address = {London, U.K.}, url = {http://recherche.ign.fr/labos/matis/pdf/articles_conf/2009/bmvc_final_09.pdf}, keyword = {} }

5 - Lidar Waveform Modeling using a Marked Point Process. C. Mallet and F. Lafarge and F. Bretar and U. Soergel and C. Heipke. In Proc. IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, November 2009. Keywords : 3D point cloud, Lidar, Marked point process, RJMCMC. @INPROCEEDINGS{mallet_icip09, author = {Mallet, C. and Lafarge, F. and Bretar, F. and Soergel, U. and Heipke, C.}, title = {Lidar Waveform Modeling using a Marked Point Process}, year = {2009}, month = {November}, booktitle = {Proc. IEEE International Conference on Image Processing (ICIP)}, address = {Cairo, Egypt}, url = {http://dx.doi.org/10.1109/ICIP.2009.5413380}, keyword = {3D point cloud, Lidar, Marked point process, RJMCMC} } Abstract : Lidar waveforms are 1D signal consisting of a train of echoes where each of them correspond to a scattering target of the Earth surface. Modeling these echoes with the appropriate parametric function is necessary to retrieve physical information about these objects and characterize their properties. This paper presents a marked point process based model to reconstruct a lidar signal in terms of a set of parametric functions. The model takes into account both a data term which measures the coherence between the models and the waveforms, and a regularizing term which introduces physical knowledge on the reconstructed signal. We search for the best configuration of functions by performing a Reversible Jump Markov Chain Monte Carlo sampler coupled with a simulated annealing. Results are finally presented on different kinds of signals in urban areas.

6 - Texture representation by geometric objects using a jump-diffusion process. F. Lafarge and G. Gimel'farb. In Proc. British Machine Vision Conference (BMVC), Leeds, U.K., November 2008. @INPROCEEDINGS{lafarge_bmvc08, author = {Lafarge, F. and Gimel'farb, G.}, title = {Texture representation by geometric objects using a jump-diffusion process}, year = {2008}, month = {November}, booktitle = {Proc. British Machine Vision Conference (BMVC)}, address = {Leeds, U.K.}, url = {http://www.comp.leeds.ac.uk/bmvc2008/proceedings/papers/86.pdf}, keyword = {} }

7 - A Geometric Primitive Extraction Process for Remote Sensing Problems.. F. Lafarge and G. Gimel'farb and X. Descombes. In Proc. Advanced Concepts for Intelligent Vision Systems, pages 518-529, Juan-les-Pins, France, October 2008. Copyright : @INPROCEEDINGS{LGF2008, author = {Lafarge, F. and Gimel'farb, G. and Descombes, X.}, title = {A Geometric Primitive Extraction Process for Remote Sensing Problems.}, year = {2008}, month = {October}, booktitle = {ACIVS}, pages = {518-529}, address = {Juan-les-Pins, France}, pdf = {http://www.springerlink.com/content/b228321527177226/}, keyword = {} }

8 - A new computationally efficient stochastic approach for building reconstruction from satellite data. F. Lafarge and M. Durupt and X. Descombes and J. Zerubia and M. Pierrot-Deseilligny. In XXI ISPRS Congress, Part A, Beijing, China, July 2008. Note : Copyright ISPRS Keywords : 3D reconstruction, Building, satellite data, stochastic approach, jump process. @INPROCEEDINGS{lafarge_isprs08, author = {Lafarge, F. and Durupt, M. and Descombes, X. and Zerubia, J. and Pierrot-Deseilligny, M.}, title = {A new computationally efficient stochastic approach for building reconstruction from satellite data}, year = {2008}, month = {July}, booktitle = {XXI ISPRS Congress, Part A}, address = {Beijing, China}, note = {Copyright ISPRS}, url = {http://www.isprs.org/proceedings/XXXVII/congress/3_pdf/40.pdf}, keyword = {3D reconstruction, Building, satellite data, stochastic approach, jump process} }

9 - Building reconstruction from a single DEM. F. Lafarge and X. Descombes and J. Zerubia and M. Pierrot-Deseilligny. In Proc. IEEE Computer Vision and Pattern Recognition (CVPR), Anchorage, Alaska, U.S., June 2008. @INPROCEEDINGS{lafarge_cvpr08, author = {Lafarge, F. and Descombes, X. and Zerubia, J. and Pierrot-Deseilligny, M.}, title = {Building reconstruction from a single DEM}, year = {2008}, month = {June}, booktitle = {Proc. IEEE Computer Vision and Pattern Recognition (CVPR)}, address = {Anchorage, Alaska, U.S.}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2008_lafarge_cvpr08.pdf}, keyword = {} }

10 - Automatic 3D modeling of urban scenes from satellite images. F. Lafarge and X. Descombes and J. Zerubia and M. Pierrot-Deseilligny. In Proc. SPACEAPPLI, Toulouse, France, April 2008. @INPROCEEDINGS{lafarge_spaceappli08, author = {Lafarge, F. and Descombes, X. and Zerubia, J. and Pierrot-Deseilligny, M.}, title = {Automatic 3D modeling of urban scenes from satellite images}, year = {2008}, month = {April}, booktitle = {Proc. SPACEAPPLI}, address = {Toulouse, France}, url = {http://www.toulousespaceshow.eu/tss08/spaceappli08/index.htm}, keyword = {} }

11 - Forest Fire Detection based on Gaussian field analysis. F. Lafarge and X. Descombes and J. Zerubia. In Proc. European Signal Processing Conference (EUSIPCO), Poznan, Poland, September 2007. Note : Copyright EURASIP Keywords : Gaussian Field, DT-caracteristic, Forest fires. @INPROCEEDINGS{lafarge_eusipco07, author = {Lafarge, F. and Descombes, X. and Zerubia, J.}, title = {Forest Fire Detection based on Gaussian field analysis}, year = {2007}, month = {September}, booktitle = {Proc. European Signal Processing Conference (EUSIPCO)}, address = {Poznan, Poland}, note = {Copyright EURASIP}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2007_lafarge_eusipco07.pdf}, keyword = {Gaussian Field, DT-caracteristic, Forest fires} }

top of the page

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

These pages were generated by