|
|
Publications of Florent Lafarge
Result of the query in the list of publications :
18 Conference articles |
12 - 3D city modeling based on Hidden Markov Model.
F. Lafarge and X. Descombes and J. Zerubia and M. Pierrot-Deseilligny. In Proc. IEEE International Conference on Image Processing (ICIP), San Antonio, U.S., September 2007.
Note : Copyright IEEE
Keywords : 3D reconstruction, Building, Hidden Markov Model.
@INPROCEEDINGS{lafarge_icip07,
|
| author |
= |
{Lafarge, F. and Descombes, X. and Zerubia, J. and Pierrot-Deseilligny, M.}, |
| title |
= |
{3D city modeling based on Hidden Markov Model}, |
| year |
= |
{2007}, |
| month |
= |
{September}, |
| booktitle |
= |
{Proc. IEEE International Conference on Image Processing (ICIP)}, |
| address |
= |
{San Antonio, U.S.}, |
| note |
= |
{Copyright IEEE}, |
| url |
= |
{http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4379207}, |
| keyword |
= |
{3D reconstruction, Building, Hidden Markov Model} |
| } |
|
13 - Rectangular Road Marking Detection with Marked Point Processes.
O. Tournaire and N. Paparoditis and F. Lafarge. In ISPRS Conference Photogrammetric Image Analysis (PIA), Vol. 36, pages 149--154, Org. IAPRS, Munich, Germany, September 2007.
@INPROCEEDINGS{tournaire_pia07,
|
| author |
= |
{Tournaire, O. and Paparoditis, N. and Lafarge, F.}, |
| title |
= |
{Rectangular Road Marking Detection with Marked Point Processes}, |
| year |
= |
{2007}, |
| month |
= |
{September}, |
| booktitle |
= |
{ISPRS Conference Photogrammetric Image Analysis (PIA)}, |
| volume |
= |
{36}, |
| pages |
= |
{149--154}, |
| organization |
= |
{IAPRS}, |
| address |
= |
{Munich, Germany}, |
| pdf |
= |
{http://www-sop.inria.fr/ariana/Publis/2007-tournaire-pia.pdf}, |
| keyword |
= |
{} |
| } |
|
14 - An Automatic Building Reconstruction Method : A Structural Approach Using High Resolution Images.
F. Lafarge and X. Descombes and J. Zerubia and M. Pierrot-Deseilligny. In Proc. IEEE International Conference on Image Processing (ICIP), Atlanta, October 2006.
Keywords : 3D reconstruction, Buildings, RJMCMC, Structural approach, Satellite images.
Copyright : IEEE
@INPROCEEDINGS{lafarge_icip06,
|
| author |
= |
{Lafarge, F. and Descombes, X. and Zerubia, J. and Pierrot-Deseilligny, M.}, |
| title |
= |
{An Automatic Building Reconstruction Method : A Structural Approach Using High Resolution Images}, |
| year |
= |
{2006}, |
| month |
= |
{October}, |
| booktitle |
= |
{Proc. IEEE International Conference on Image Processing (ICIP)}, |
| address |
= |
{Atlanta}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/2006_lafarge_icip06.pdf}, |
| keyword |
= |
{3D reconstruction, Buildings, RJMCMC, Structural approach, Satellite images} |
| } |
|
15 - Automatic 3D Building Reconstruction from DEMs: an Application to PLEIADES Simulations.
F. Lafarge and X. Descombes and J. Zerubia and M. Pierrot-Deseilligny. In Proc. International Society for Photogrammetry and Remote Sensing Commission I Symposium (ISPRS), Marne La Vallee, France, July 2006.
Keywords : 3D reconstruction, Digital Elevation Model, Building extraction, Dense urban areas, PLEIADES simulations.
@INPROCEEDINGS{lafarge_isprs06,
|
| author |
= |
{Lafarge, F. and Descombes, X. and Zerubia, J. and Pierrot-Deseilligny, M.}, |
| title |
= |
{Automatic 3D Building Reconstruction from DEMs: an Application to PLEIADES Simulations}, |
| year |
= |
{2006}, |
| month |
= |
{July}, |
| booktitle |
= |
{Proc. International Society for Photogrammetry and Remote Sensing Commission I Symposium (ISPRS)}, |
| address |
= |
{Marne La Vallee, France}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/2006_lafarge_isprs06.pdf}, |
| keyword |
= |
{3D reconstruction, Digital Elevation Model, Building extraction, Dense urban areas, PLEIADES simulations} |
| } |
|
16 - An Automatic 3D City Model : a Bayesian Approach using Satellite Images.
F. Lafarge and X. Descombes and J. Zerubia and M. Pierrot-Deseilligny. In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toulouse, France, May 2006.
Note : Copyright IEEE
Keywords : 3D reconstruction, Buildings, MCMC, Digital Elevation Model (DEM).
@INPROCEEDINGS{florenticassp06,
|
| author |
= |
{Lafarge, F. and Descombes, X. and Zerubia, J. and Pierrot-Deseilligny, M.}, |
| title |
= |
{An Automatic 3D City Model : a Bayesian Approach using Satellite Images}, |
| year |
= |
{2006}, |
| month |
= |
{May}, |
| booktitle |
= |
{Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, |
| address |
= |
{Toulouse, France}, |
| note |
= |
{Copyright IEEE}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/2006_florenticassp06.pdf}, |
| keyword |
= |
{3D reconstruction, Buildings, MCMC, Digital Elevation Model (DEM)} |
| } |
|
17 - Détection de feux de forêt à partir d'images satellitaires IRT par analyse statistique d'évènements rares.
F. Lafarge and X. Descombes and J. Zerubia and S. Mathieu-Marni. In Proc. GRETSI Symposium on Signal and Image Processing, Louvain-la-Neuve, Belgique, September 2005.
Keywords : Rare event, Forest fires, Gaussian Field.
@INPROCEEDINGS{lafarge_gretsi05,
|
| author |
= |
{Lafarge, F. and Descombes, X. and Zerubia, J. and Mathieu-Marni, S.}, |
| title |
= |
{Détection de feux de forêt à partir d'images satellitaires IRT par analyse statistique d'évènements rares}, |
| year |
= |
{2005}, |
| month |
= |
{September}, |
| booktitle |
= |
{Proc. GRETSI Symposium on Signal and Image Processing}, |
| address |
= |
{Louvain-la-Neuve, Belgique}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/2005_lafarge_gretsi05.pdf}, |
| keyword |
= |
{Rare event, Forest fires, Gaussian Field} |
| } |
|
18 - Textural Kernel for SVM Classification in Remote Sensing : Application to Forest Fire Detection and Urban Area Extraction.
F. Lafarge and X. Descombes and J. Zerubia. In Proc. IEEE International Conference on Image Processing (ICIP), Genoa, Italy, September 2005.
Keywords : Support Vector Machines, Learning base, Markov Fields, Forest fires, Urban areas.
Copyright : IEEE
@INPROCEEDINGS{lafarge_icip05,
|
| author |
= |
{Lafarge, F. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Textural Kernel for SVM Classification in Remote Sensing : Application to Forest Fire Detection and Urban Area Extraction}, |
| year |
= |
{2005}, |
| month |
= |
{September}, |
| booktitle |
= |
{Proc. IEEE International Conference on Image Processing (ICIP)}, |
| address |
= |
{Genoa, Italy}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/2005_lafarge_icip05.pdf}, |
| keyword |
= |
{Support Vector Machines, Learning base, Markov Fields, Forest fires, Urban areas} |
| } |
|
 top of the page
5 Technical and Research Reports |
1 - A structural approach for 3D building reconstruction.
F. Lafarge and X. Descombes and J. Zerubia and M. Pierrot-Deseilligny. Research Report 6048, INRIA, November 2006.
Keywords : 3D reconstruction, Structural approach, Building, RJMCMC, Viterbi.
@TECHREPORT{Lafarge_rr_6048,
|
| author |
= |
{Lafarge, F. and Descombes, X. and Zerubia, J. and Pierrot-Deseilligny, M.}, |
| title |
= |
{A structural approach for 3D building reconstruction}, |
| year |
= |
{2006}, |
| month |
= |
{November}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{6048}, |
| url |
= |
{https://hal.inria.fr/inria-00114338}, |
| pdf |
= |
{ftp://ftp-sop.inria.fr/ariana/Articles/2006_Lafarge_rr_6048.pdf}, |
| keyword |
= |
{3D reconstruction, Structural approach, Building, RJMCMC, Viterbi} |
| } |
|
2 - 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)} |
| } |
|
3 - A Parametric Model for Automatic 3D Building Reconstruction from High Resolution Satellite Images.
F. Lafarge and X. Descombes and J. Zerubia and M. Pierrot-Deseilligny. Research Report 5687, INRIA, France, September 2005.
Keywords : 3D reconstruction, Buildings, RJMCMC, Digital Elevation Model (DEM).
@TECHREPORT{5687,
|
| author |
= |
{Lafarge, F. and Descombes, X. and Zerubia, J. and Pierrot-Deseilligny, M.}, |
| title |
= |
{A Parametric Model for Automatic 3D Building Reconstruction from High Resolution Satellite Images}, |
| year |
= |
{2005}, |
| month |
= |
{September}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{5687}, |
| address |
= |
{France}, |
| url |
= |
{http://hal.inria.fr/inria-00070326/fr/}, |
| pdf |
= |
{https://hal.inria.fr/file/index/docid/70326/filename/RR-5687.pdf}, |
| ps |
= |
{http://hal.inria.fr/docs/00/07/03/26/PS/RR-5687.ps}, |
| keyword |
= |
{3D reconstruction, Buildings, RJMCMC, Digital Elevation Model (DEM)} |
| } |
Résumé :
Dans ce rapport, nous développons un modèle paramétrique pour la reconstruction automatique de bâtiments en 3D fondé sur une approche bayésienne à partir de simulations PLEIADES. Les images satellitaires haute résolution représentent un nouveau type de données permettant de traiter les problèmes de reconstruction 3D de bâtiments. Leur résolution ``relativement basse'' et leur faible rapport signal sur bruit pour ce type de problèmes ne permet pas l'utilisation des méthodes standard développées dans le cas des images aériennes. Nous proposons une approche paramétrique utilisant des Modèles Numériques d'Elévation (MNE) et les empreintes de bâtiments associées modélisées par rectangles. La méthode proposée est fondée sur une approche bayésienne. Une technique de type de Monte Carlo par Chaînes de Markov est utilisée afin d'optimiser le modèle énergétique. |
Abstract :
This report develops a parametric model for automatic 3D building reconstruction based on a Bayesian approach from PLEIADES simulations. High resolution satellite images are a new kind of data to deal with 3D building reconstruction problems. Their ``relatively low'' resolution and low signal noise ration do not allow to use standard methods developed for the aerial image case. We propose a parametric approach using Digital Elevation Models (DEM) and associated rectangular building footprints. The proposed method is based on a Bayesian approach. A Markov Chain Monte Carlo technique is used to optimize the energy model. |
|
4 - Détection de Feux de Forêt par Analyse Statistique de la Radiométrie d'Images Satellitaires.
F. Lafarge and X. Descombes and J. Zerubia. Research Report 5369, INRIA, France, December 2004.
Keywords : Forest fires, Gaussian Field, Rare event.
@TECHREPORT{5369,
|
| author |
= |
{Lafarge, F. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Détection de Feux de Forêt par Analyse Statistique de la Radiométrie d'Images Satellitaires}, |
| year |
= |
{2004}, |
| month |
= |
{December}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{5369}, |
| address |
= |
{France}, |
| url |
= |
{https://hal.inria.fr/inria-00070634}, |
| pdf |
= |
{https://hal.inria.fr/file/index/docid/70634/filename/RR-5369.pdf}, |
| ps |
= |
{https://hal.inria.fr/docs/00/07/06/34/PS/RR-5369.ps}, |
| keyword |
= |
{Forest fires, Gaussian Field, Rare event} |
| } |
Résumé :
Nous proposons, dans ce rapport, une méthode de détection des feux de forêt par imagerie satellitaire fondée sur la théorie des champs aléatoires. L'idée consiste à modéliser l'image par une réalisation d'un champ gaussien afin d'en extraire, par une analyse statistique, les éléments étrangers pouvant correspondre aux feux.
Le canal IRT (InfraRouge Thermique) contient des longueurs d'onde particulièrement sensibles à l'émission de chaleur. L'intensité d'un pixel d'une image IRT est donc d'autant plus forte que la température de la zone associée à ce pixel est élevée. Les feux de forêt peuvent alors être caractérisés par des pics d'intensité sur ce type d'images. Nous proposons une méthode de classification non supervisée et automatique fondée sur la théorie des champs gaussiens. Pour ce faire, nous modélisons dans un premier temps l'image par une réalisation d'un champ gaussien. Les zones de feux, minoritaires et de fortes intensités sont considérées comme des éléments étrangers à ce champ : ce sont des évènements rares. Ensuite, par une analyse statistique, nous déterminons un jeu de probabilités définissant, pour une zone donnée de l'image, un degré d'appartenance au champ gaussien, et par complémentarité aux zones potentiellement en feux. |
Abstract :
We present in this report a method for forest fire detection in satellite images based on random field theory. The idea is to model the image as a realization of a gaussian field in order to extract the rare events, which are potential fires, by a statistical analysis.
The TIR (Thermical InfraRed) channel has a wavelength sensitive to the emission of heat : the higher the heat of a area, the higher the intensity of the corresponding pixel of the image. Then a forest fire can be characterized by peak intensity in TIR images. We present an fully automatic unsupervised classification method based on Gaussian field theory. First we model the image as a realization of a Gaussian field. The fire areas, which have high intensity and are supposed to be a minority, are considered as foreign elements of that field : they are rare events. Then we determine by a statistical analysis a set of probabilities which characterizes the degree of belonging to the Gaussian field of a small area of the image. So, we estimate the probability that the area is a potential fire. |
|
5 - Noyaux Texturaux pour les Problèmes de Classification par SVM en Télédétection.
F. Lafarge and X. Descombes and J. Zerubia. Research Report 5370, INRIA, France, December 2004.
Keywords : Support Vector Machines, Classification, Forest fires, Urban areas, Learning base, Markov Fields.
@TECHREPORT{5370,
|
| author |
= |
{Lafarge, F. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Noyaux Texturaux pour les Problèmes de Classification par SVM en Télédétection}, |
| year |
= |
{2004}, |
| month |
= |
{December}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{5370}, |
| address |
= |
{France}, |
| url |
= |
{https://hal.inria.fr/inria-00070633}, |
| pdf |
= |
{https://hal.inria.fr/file/index/docid/70633/filename/RR-5370.pdf}, |
| ps |
= |
{https://hal.inria.fr/docs/00/07/06/33/PS/RR-5370.ps}, |
| keyword |
= |
{Support Vector Machines, Classification, Forest fires, Urban areas, Learning base, Markov Fields} |
| } |
Résumé :
Nous détaillons dans ce rapport la construction de deux noyaux texturaux s'utilisant dans les problèmes de classification par «Support Vector Machines» en télédétection. Les SVM constituent une méthode de classification supervisée particulièrement bien adaptée pour traiter des données de grande dimension telles que les images satellitaires. Par cette méthode, nous souhaitons réaliser l'apprentissage de paramètres qui permettent la différenciation entre deux ensembles de pixels connexes non-identiques. Nous travaillons pour cela sur des fonctions noyaux, fonctions caractérisant une certaine similarité entre deux données. Dans notre cas, cette similarité sera fondée à la fois sur une notion radiométrique et sur une notion texturale. La principale difficulté rencontrée dans cette étude réside dans l'élaboration de paramètres texturaux pertinents qui modélisent au mieux l'homogénéité d'un ensemble de pixels connexes. Nous appliquons les noyaux proposés à deux problèmes de télédétection: la détection de feux de forêt et la détection de zones urbaines à partir d'images satellitaires haute résolusion. |
Abstract :
We present in this report two textural kernels for «Support Vector Machines» classification applied to remote sensing problems. SVMs constitute a method of supervised classification well adapted to deal with data of high dimension, such as images. We would like to learn parameters which allow the differentiation between two sets of connected pixels. We also introduce kernel functions which characterize a notion of similarity between two pieces of data. In our case this similarity is based on a radiometric charateristic and a textural characteristic. The main difficulty is to elaborate textural parameters which are pertinent and characterize as well as possible the homogeneity of a set of connected pixels. We apply this method to remote sensing problems : the detection of forest fires and the extraction of urban areas in high resolution satellite images. |
|
top of the page
These pages were generated by 
|
2011 Activity report
get the bibtex
