Publications of Xavier Descombes

Result of the query in the list of publications :

• 44 Articles
• 1 PhD Thesis and Habilitation
• 97 Conference articles
• 36 Technical and Research Reports
• 7 Collection articles or Books chapters
• 2 Books

new search | get the bibtex

navigation : 1 - 2 - 3 - 4 display : 10 per page | 20 per page | 50 per page

97 Conference articles

6 - A novel algorithm for occlusions and perspective effects using a 3d object process. A. Gamal Eldin and X. Descombes and J. Zerubia. In ICASSP 2011 (International Conference on Acoustics, Speech and Signal Processing), Prague, Czech Republic, May 2011. Keywords : Occlusions, 3D object process, multiple object extraction, Multiple Birth and Death, Penguins Counting. @INPROCEEDINGS{ICASSP_2011, author = {Gamal Eldin, A. and Descombes, X. and Zerubia, J.}, title = {A novel algorithm for occlusions and perspective effects using a 3d object process}, year = {2011}, month = {May}, booktitle = {ICASSP 2011 (International Conference on Acoustics, Speech and Signal Processing)}, address = {Prague, Czech Republic}, url = {http://hal.inria.fr/inria-00592449/fr/}, keyword = {Occlusions, 3D object process, multiple object extraction, Multiple Birth and Death, Penguins Counting} } Abstract : In this paper, we introduce a novel probabilistic approach to handle occlusions and perspective effects. The proposed method is an object based method embedded in a marked point process framework. We apply it for the size estimation of a penguin colony, where we model a penguin colony as an unknown number of 3D objects. The main idea of the proposed approach is to sample some candidate configurations consisting of 3D objects lying in the real plane. A Gibbs energy is define on the configuration space, which takes into account both prior and data information. These configurations are projected onto the image plane. The configurations are modified until convergence using the multiple birth and death optimization algorithm and by measuring the similarity between the projected image of the configuration and the real image. During optimization, the proposed configuration is modeled by a mixed graph which represents all dependencies between the objects, including interaction between neighbor objects and parent-child dependency for occluded objects. We tested our model on synthetic image, and real images.

7 - Brain tumor vascular network segmentation from micro-tomography. X. Descombes and F. Plouraboue and El Boustani Habdelhkim and Fonta Caroline and |LeDuc Geraldine and Serduc Raphael and Weitkamp Timm. In Internation Symposium of Biomedical Imaging (ISBI), Chicago, USA, April 2011. Keywords : Segmentation, Markov random field, Tomography, Brain, vascular network. Copyright : IEEE @INPROCEEDINGS{isbi11, author = {Descombes, X. and Plouraboue, F. and Boustani Habdelhkim, El and Caroline, Fonta and Geraldine, |LeDuc and Raphael, Serduc and Timm, Weitkamp}, title = {Brain tumor vascular network segmentation from micro-tomography}, year = {2011}, month = {April}, booktitle = {Internation Symposium of Biomedical Imaging (ISBI)}, address = {Chicago, USA}, url = {http://dx.doi.org/10.1109/ISBI.2011.5872596}, keyword = {Segmentation, Markov random field, Tomography, Brain, vascular network} } Abstract : Micro-tomography produces high resolution images of biological structures such as vascular networks. In this paper, we present a new approach for segmenting vascular network into pathological and normal regions from considering their micro-vessel 3D structure only. We define and use a conditional random field for segmenting the output of a watershed algorithm. The tumoral and normal classes are thus characterized by their respective distribution of watershed region size interpreted as local vascular territories.

8 - Multiple Birth and Cut Algorithm for Point Process Optimization. A. Gamal Eldin and X. Descombes and J. Zerubia. In Proc. IEEE International Conference on Signal-Image Technology and Internet-based Systems (SITIS), Kuala Lumpur, Malaysia, December 2010. Keywords : Multiple Birth and Cut, Graph Cut, Multiple Birth and Death, Marked point process. @INPROCEEDINGS{MBC_MPP_SITIS10, author = {Gamal Eldin, A. and Descombes, X. and Zerubia, J.}, title = {Multiple Birth and Cut Algorithm for Point Process Optimization}, year = {2010}, month = {December}, booktitle = {Proc. IEEE International Conference on Signal-Image Technology and Internet-based Systems (SITIS)}, address = {Kuala Lumpur, Malaysia}, url = {http://hal.archives-ouvertes.fr/inria-00516305/fr/}, keyword = {Multiple Birth and Cut, Graph Cut, Multiple Birth and Death, Marked point process} } Abstract : In this paper, we describe a new optimization method which we call Multiple Birth and Cut (MBC). It combines the recently developed Multiple Birth and Death (MBD) algorithm and the Graph-Cut algorithm. MBD and MBC optimization methods are applied to the energy minimization of an object based model, the marked point process. We compare the MBC to the MBD showing the advantages and disadvantages, where the most important advantage is the reduction of the number of parameters. We validated our algorithm on the counting problem of flamingos in colony, where our algorithm outperforms the performance of the MBD algorithm.

9 - Parameter estimation for a marked point process within a framework of multidimensional shape extraction from remote sensing images. S. Ben Hadj and F. Chatelain and X. Descombes and J. Zerubia. In Proc. ISPRS Technical Commission III Symposium on Photogrammetry Computer Vision and Image Analysis (PCV), Paris, France, September 2010. Keywords : Shape extraction, Marked point process, RJMCMC, Simulated Annealing, Stochastic EM (SEM). @INPROCEEDINGS{sbenhadj10a, author = {Ben Hadj, S. and Chatelain, F. and Descombes, X. and Zerubia, J.}, title = {Parameter estimation for a marked point process within a framework of multidimensional shape extraction from remote sensing images}, year = {2010}, month = {September}, booktitle = {Proc. ISPRS Technical Commission III Symposium on Photogrammetry Computer Vision and Image Analysis (PCV)}, address = {Paris, France}, url = {http://hal.archives-ouvertes.fr/docs/00/52/63/45/PDF/ISPRS_SBH_FC_XD_JZ_Final2.pdf}, keyword = {Shape extraction, Marked point process, RJMCMC, Simulated Annealing, Stochastic EM (SEM)} }

10 - Tree crown detection in high resolution optical and LiDAR images of tropical forest. J. Zhou and C. Proisy and X. Descombes and I. Hedhli and N. Barbier and J. Zerubia and J.-P. Gastellu-Etchegorry and P. Couteron. In Proc. SPIE Symposium on Remote Sensing, Toulouse, France, September 2010. Keywords : Tropical forest, tree detection, Marked point process. @INPROCEEDINGS{Zhou10, author = {Zhou, J. and Proisy, C. and Descombes, X. and Hedhli, I. and Barbier, N. and Zerubia, J. and Gastellu-Etchegorry, J.-P. and Couteron, P.}, title = {Tree crown detection in high resolution optical and LiDAR images of tropical forest}, year = {2010}, month = {September}, booktitle = {Proc. SPIE Symposium on Remote Sensing}, address = {Toulouse, France}, url = {http://dx.doi.org/10.1117/12.865068}, keyword = {Tropical forest, tree detection, Marked point process} }

11 - Multi-spectral Image Analysis for Skin Pigmentation Classification. S. Prigent and X. Descombes and D. Zugaj and P. Martel and J. Zerubia. In Proc. IEEE International Conference on Image Processing (ICIP), Hong-Kong, China, September 2010. Keywords : skin hyper-pigmentation, Multi-spectral images, Support Vector Machines, Independant Component Analysis, Data reduction. @INPROCEEDINGS{sp02, author = {Prigent, S. and Descombes, X. and Zugaj, D. and Martel, P. and Zerubia, J.}, title = {Multi-spectral Image Analysis for Skin Pigmentation Classification}, year = {2010}, month = {September}, booktitle = {Proc. IEEE International Conference on Image Processing (ICIP)}, address = {Hong-Kong, China}, pdf = {http://hal.inria.fr/docs/00/49/94/92/PDF/Article_ICIP.pdf}, keyword = {skin hyper-pigmentation, Multi-spectral images, Support Vector Machines, Independant Component Analysis, Data reduction} } Abstract : In this paper, we compare two different approaches for semi-automatic detection of skin hyper-pigmentation on multi-spectral images. These two methods are support vector machine (SVM) and blind source separation. To apply SVM, a dimension reduction method adapted to data classification is proposed. It allows to improve the quality of SVM classification as well as to have reasonable computation time. For the blind source separation approach we show that, using independent component analysis, it is possible to extract a relevant cartography of skin pigmentation.

12 - Building Detection in a Single Remotely Sensed Image with a Point Process of Rectangles. C. Benedek and X. Descombes and J. Zerubia. In Proc. International Conference on Pattern Recognition (ICPR), Istanbul, Turkey, August 2010. Keywords : Marked point process, multiple birth-and-death dynamics, Building extraction. @INPROCEEDINGS{benedekICPR10, author = {Benedek, C. and Descombes, X. and Zerubia, J.}, title = {Building Detection in a Single Remotely Sensed Image with a Point Process of Rectangles}, year = {2010}, month = {August}, booktitle = {Proc. International Conference on Pattern Recognition (ICPR)}, address = {Istanbul, Turkey}, pdf = {http://hal.archives-ouvertes.fr/inria-00481019/en/}, keyword = {Marked point process, multiple birth-and-death dynamics, Building extraction} } Abstract : In this paper we introduce a probabilistic approach of building extraction in remotely sensed images. To cope with data heterogeneity we construct a flexible hierarchical framework which can create various building appearance models from different elementary feature based modules. A global optimization process attempts to find the optimal configuration of buildings, considering simultaneously the observed data, prior knowledge, and interactions between the neighboring building parts. The proposed method is evaluated on various aerial image sets containing more than 500 buildings, and the results are matched against two state-of-the-art techniques.

13 - Spectral Analysis and Unsupervised SVM Classification for Skin Hyper-pigmentation Classification. S. Prigent and X. Descombes and D. Zugaj and J. Zerubia. In Proc. IEEE Workshop on Hyperspectral Image and Signal Processing : Evolution in Remote Sensing (WHISPERS), Reykjavik, Iceland, June 2010. Keywords : Sectral analysis, Data reduction, Projection pursuit, Support Vector Machines, skin hyper-pigmentation. @INPROCEEDINGS{sp01, author = {Prigent, S. and Descombes, X. and Zugaj, D. and Zerubia, J.}, title = {Spectral Analysis and Unsupervised SVM Classification for Skin Hyper-pigmentation Classification}, year = {2010}, month = {June}, booktitle = {Proc. IEEE Workshop on Hyperspectral Image and Signal Processing : Evolution in Remote Sensing (WHISPERS)}, address = {Reykjavik, Iceland}, pdf = {http://hal.inria.fr/docs/00/49/55/60/PDF/whispers2010_submission_124.pdf}, keyword = {Sectral analysis, Data reduction, Projection pursuit, Support Vector Machines, skin hyper-pigmentation} } Abstract : Data reduction procedures and classification via support vector machines (SVMs) are often associated with multi or hyperspectral image analysis. In this paper, we propose an automatic method with these two schemes in order to perform a classification of skin hyper-pigmentation on multi-spectral images. We propose a spectral analysis method to partition the spectrum as a tool for data reduction, implemented by projection pursuit. Once the data is reduced, an SVM is used to differentiate the pathological from the healthy areas. As SVM is a supervised classification method, we propose a spatial criterion for spectral analysis in order to perform automatic learning.

14 - Extraction of arbitrarily shaped objects using stochastic multiple birth-and-death dynamics and active contours. M. S. Kulikova and I. H. Jermyn and X. Descombes and E. Zhizhina and J. Zerubia. In Proc. IS&T/SPIE Electronic Imaging, San Jose, USA, January 2010. Keywords : Object extraction, Marked point process, Shape prior, Active contour, birth-and-death dynamics. Copyright : Copyright 2010 by SPIE and IS&T. This paper was published in the proceedings of IS&T/SPIE Electronic Imaging 2010 Conference in San Jose, USA, and is made available as an electronic reprint with permission of SPIE and IS&T. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. @INPROCEEDINGS{Kulikova10a, author = {Kulikova, M. S. and Jermyn, I. H. and Descombes, X. and Zhizhina, E. and Zerubia, J.}, title = {Extraction of arbitrarily shaped objects using stochastic multiple birth-and-death dynamics and active contours}, year = {2010}, month = {January}, booktitle = {Proc. IS&T/SPIE Electronic Imaging}, address = {San Jose, USA}, pdf = {http://hal.archives-ouvertes.fr/docs/00/46/54/72/PDF/Kulikova_SPIE2010.pdf}, keyword = {Object extraction, Marked point process, Shape prior, Active contour, birth-and-death dynamics} } Abstract : We extend the marked point process models that have been used for object extraction from images to arbitrarily shaped objects, without greatly increasing the computational complexity of sampling and estimation. From an alternative point of view, the approach can be viewed as an extension of the active contour methodology to an a priori unknown number of objects. Sampling and estimation are based on a stochastic birth-and-death process defined on the configuration space of an arbitrary number of objects, where the objects are defined by the image data and prior information. The performance of the approach is demonstrated via experimental results on synthetic and real data.

15 - A marked point process model with strong prior shape information for extraction of multiple, arbitrarily-shaped objects. M. S. Kulikova and I. H. Jermyn and X. Descombes and E. Zhizhina and J. Zerubia. In Proc. IEEE SITIS, Publ. IEEE Computer Society, Marrakech, Maroc, December 2009. Keywords : Object extraction, Marked point process, Shape prior, Active contour, multiple birth-and-death dynamics. @INPROCEEDINGS{Kulikova09a, author = {Kulikova, M. S. and Jermyn, I. H. and Descombes, X. and Zhizhina, E. and Zerubia, J.}, title = {A marked point process model with strong prior shape information for extraction of multiple, arbitrarily-shaped objects}, year = {2009}, month = {December}, booktitle = {Proc. IEEE SITIS}, publisher = {IEEE Computer Society}, address = {Marrakech, Maroc}, pdf = {http://hal.inria.fr/docs/00/43/63/20/PDF/PID1054029.pdf}, keyword = {Object extraction, Marked point process, Shape prior, Active contour, multiple birth-and-death dynamics} } Abstract : We define a method for incorporating strong prior shape information into a recently extended Markov point process model for the extraction of arbitrarily-shaped objects from images. To estimate the optimal configuration of objects, the process is sampled using a Markov chain based on a stochastic birth-and-death process defined in a space of multiple objects. The single objects considered are defined by both the image data and the prior information in a way that controls the computational complexity of the estimation problem. The method is tested via experiments on a very high resolution aerial image of a scene composed of tree crowns.

16 - Building Extraction and Change Detection in Multitemporal Remotely Sensed Images with Multiple Birth and Death Dynamics. C. Benedek and X. Descombes and J. Zerubia. In IEEE Workshop on Applications of Computer Vision (WACV), pages 100-105, Snowbird, Utah, USA, December 2009. Keywords : Marked point process, Change detection, Aerial images, Building extraction, Satellite images. @INPROCEEDINGS{benedekWacv09, author = {Benedek, C. and Descombes, X. and Zerubia, J.}, title = {Building Extraction and Change Detection in Multitemporal Remotely Sensed Images with Multiple Birth and Death Dynamics}, year = {2009}, month = {December}, booktitle = {IEEE Workshop on Applications of Computer Vision (WACV)}, pages = {100-105}, address = {Snowbird, Utah, USA}, pdf = {http://hal.archives-ouvertes.fr/docs/00/42/66/18/PDF/benedekWACV09.pdf}, keyword = {Marked point process, Change detection, Aerial images, Building extraction, Satellite images} } Abstract : In this paper we introduce a new probabilistic method which integrates building extraction with change detection in remotely sensed image pairs. A global optimization process attempts to find the optimal configuration of buildings, considering the observed data, prior knowledge, and interactions between the neighboring building parts. The accuracy is ensured by a Bayesian object model verification, meanwhile the computational cost is significantly decreased by a non-uniform stochastic object birth process, which proposes relevant objects with higher probability based on low-level image features.

17 - Reconstruction 3D du bâti par la technique des ombres chinoises. P. Lukashevish and A. Kraushonak and X. Descombes and J.D. Durou and B. Zalessky and E. Zhizhina. In GRETSI Dijon, Dijon, France, November 2009. Keywords : 3D reconstruction. @INPROCEEDINGS{luka09, author = {Lukashevish, P. and Kraushonak, A. and Descombes, X. and Durou, J.D. and Zalessky, B. and Zhizhina, E.}, title = {Reconstruction 3D du bâti par la technique des ombres chinoises}, year = {2009}, month = {November}, booktitle = {GRETSI Dijon}, address = {Dijon, France}, url = {http://hal.inria.fr/inria-00399208/fr/}, keyword = {3D reconstruction} }

18 - Object extraction from high resolution SAR images using a birth and death dynamics. F. Arslan and X. Descombes and J. Zerubia. In Proc. IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, November 2009. Keywords : High resolution SAR images, Object extraction, Marked point process, birth and death process. @INPROCEEDINGS{Fatih09, author = {Arslan, F. and Descombes, X. and Zerubia, J.}, title = {Object extraction from high resolution SAR images using a birth and death dynamics}, year = {2009}, month = {November}, booktitle = {Proc. IEEE International Conference on Image Processing (ICIP)}, address = {Cairo, Egypt}, url = {http://dx.doi.org/10.1109/ICIP.2009.5413907}, keyword = {High resolution SAR images, Object extraction, Marked point process, birth and death process} } Abstract : We present a new approach to extract predefined objects, such as trees and oil tanks for instance, from high resolution SAR images. We consider a stochastic approach based on an object process also called marked point process. The objects represent trees or oil tanks which are modeled by disks in the image. We first define a Gibbs density that takes into account both prior information and the data. The energy we define is composed of two terms, one is a prior, penalizing overlaps between objects, and the other is a data term, which measures the suitability of an object in the SAR image. The problem is then reduced to an energy minimization problem. We sample the process to extract the configuration of objects minimizing the energy by a fast birth-and-death dynamics, leading to the total number of objects (trees or oil tanks in our case). This approach is much faster than manual counts and does not need any preprocessing or supervision of a user.

19 - Estimation des paramètres de processus ponctuels marqués dans le cadre de l'extraction d’objets en imagerie de télédétection. F. Chatelain and X. Descombes and J. Zerubia. In Proc. Symposium on Signal and Image Processing (GRETSI), Dijon, France, November 2009. @INPROCEEDINGS{cha09a, author = {Chatelain, F. and Descombes, X. and Zerubia, J.}, title = {Estimation des paramètres de processus ponctuels marqués dans le cadre de l'extraction d’objets en imagerie de télédétection}, year = {2009}, month = {November}, booktitle = {Proc. Symposium on Signal and Image Processing (GRETSI)}, address = {Dijon, France}, url = {http://hal.inria.fr/inria-00399258/fr/}, keyword = {} }

20 - Parameter estimation for marked point processes. Application to object extraction from remote sensing images. (poster). F. Chatelain and X. Descombes and J. Zerubia. In Proc. Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), Bonn, Germany, August 2009. @INPROCEEDINGS{ChatelainEMMCVPR09, author = {Chatelain, F. and Descombes, X. and Zerubia, J.}, title = {Parameter estimation for marked point processes. Application to object extraction from remote sensing images. (poster)}, year = {2009}, month = {August}, booktitle = {Proc. Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR)}, address = {Bonn, Germany}, url = {http://link.springer.com/chapter/10.1007%2F978-3-642-03641-5_17}, keyword = {} }

21 - Conditional mixed-state model for structural change analysis from very high resolution optical images. B. Belmudez and V. Prinet and J.F. Yao and P. Bouthemy and X. Descombes. In Proc. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Cape Town, South Africa, July 2009. Keywords : Change detection, mixed Markov models. @INPROCEEDINGS{bel09, author = {Belmudez, B. and Prinet, V. and Yao, J.F. and Bouthemy, P. and Descombes, X.}, title = {Conditional mixed-state model for structural change analysis from very high resolution optical images}, year = {2009}, month = {July}, booktitle = {IGARSS}, address = {Cape Town, South Africa}, url = {http://hal.archives-ouvertes.fr/inria-00398062/}, keyword = {Change detection, mixed Markov models} } Abstract : The present work concerns the analysis of dynamic scenes from earth observation images. We are interested in building a map which, on one hand locates places of change, on the other hand, reconstructs a unique visual information of the non-change areas. We show in this paper that such a problem can naturally be takled with conditional mixed-state random field modeling (mixed-state CRF), where the ”mixed state” refers to the symbolic or continous nature of the unknown variable. The maximum a posteriori (MAP) estimation of the CRF is, through the Hammersley-Clifford theorem, turned into an energy minimisation problem. We tested the model on several Quickbird images and illustrate the quality of the results.

22 - Fast Realization of Digital Elevation Model . X. Descombes and A. Kraushonak and P. Lukashevish and B. Zalessky. In PRIP , pages 156-160, Minsk, Belarus, May 2009. @INPROCEEDINGS{KRA-09, author = {Descombes, X. and Kraushonak, A. and Lukashevish, P. and Zalessky, B.}, title = {Fast Realization of Digital Elevation Model }, year = {2009}, month = {May}, booktitle = {PRIP }, pages = {156-160}, address = {Minsk, Belarus}, url = {http://www.iapr.org/members/newsletter/Newsletter09-03/index_files/Page420.htm}, pdf = {https://hal.inria.fr/inria-00423678/document}, keyword = {} }

23 - 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 = {} }

24 - Unsupervised One-Class SVM Using a Watershed Algorithm and Hysteresis Thresholding to Detect Burnt Areas. O. Zammit and X. Descombes and J. Zerubia. In Proc. International Conference on Pattern Recognition and Image Analysis (PRIA), Nizhny Novgorod, Russia, September 2008. Keywords : Classification, Segmentation, Support Vector Machines, Burnt areas, Forest fires, Satellite images. Copyright : @INPROCEEDINGS{zammit_pria_08, author = {Zammit, O. and Descombes, X. and Zerubia, J.}, title = {Unsupervised One-Class SVM Using a Watershed Algorithm and Hysteresis Thresholding to Detect Burnt Areas}, year = {2008}, month = {September}, booktitle = {Proc. International Conference on Pattern Recognition and Image Analysis (PRIA)}, address = {Nizhny Novgorod, Russia}, pdf = {http://hal.inria.fr/inria-00316297/fr/}, keyword = {Classification, Segmentation, Support Vector Machines, Burnt areas, Forest fires, Satellite images} }

25 - Combining One-Class Support Vector Machines and hysteresis thresholding: application to burnt area mapping. O. Zammit and X. Descombes and J. Zerubia. In Proc. European Signal Processing Conference (EUSIPCO), Lausanne, Switzerland, August 2008. Note : to appear. Keywords : Classification, Satellite images, Support Vector Machines, Burnt areas, Forest fires, Clustering. Copyright : @INPROCEEDINGS{zammit_eusipco_08, author = {Zammit, O. and Descombes, X. and Zerubia, J.}, title = {Combining One-Class Support Vector Machines and hysteresis thresholding: application to burnt area mapping}, year = {2008}, month = {August}, booktitle = {Proc. European Signal Processing Conference (EUSIPCO)}, address = {Lausanne, Switzerland}, url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7080254}, keyword = {Classification, Satellite images, Support Vector Machines, Burnt areas, Forest fires, Clustering} }

26 - 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} }

27 - Indexing of mid-resolution satellite images with structural attributes. A. Bhattacharya and M. Roux and H. Maitre and I. H. Jermyn and X. Descombes and J. Zerubia. In The International Society for Photogrammetry and Remote Sensing, Beijing, China, July 2008. Keywords : Landscape, Segmentation, Features, Extraction, Classification, Modelling. @INPROCEEDINGS{Bhattacharya08, author = {Bhattacharya, A. and Roux, M. and Maitre, H. and Jermyn, I. H. and Descombes, X. and Zerubia, J.}, title = {Indexing of mid-resolution satellite images with structural attributes}, year = {2008}, month = {July}, booktitle = {The International Society for Photogrammetry and Remote Sensing}, address = {Beijing, China}, pdf = {http://www-sop.inria.fr/members/Ian.Jermyn/publications/Bhattacharya08isprs.pdf}, keyword = {Landscape, Segmentation, Features, Extraction, Classification, Modelling} } Abstract : Indexing and retrieval of satellite images 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. Entities in an image may be strongly correlated with each other and can therefore be used to characterize geographical environments on the Earth’s surface. The properties of road networks vary considerably from one geographical environment to another. The networks pertaining in a satellite image can therefore be used to classify and retrieve such environments. In the work presented in this paper we have defined 7 such classes. These classes can be categorized as follows: 2 urban classes consisting of “Urban USA” and “Urban Europe”; 3 rural classes consisting of “Villages”, “Mountains” and “Fields”; an “Airports” class and a “Common” class (this can be considered as a rejection class). These classes were then classified with the aid of geometrical and topological features computed from the road networks occurring in them. In our work we have used two extraction methods simultaneously on an image to extract the road networks pertaining in it. A set of 16 network features were computed from one extraction method and were categorized into 6 groups as follows: 6 measures of ‘density’, 4 measures of ‘curviness’, 2 measures of ‘homogeneity’, 1 measure of ‘length’, 2 measures of ‘distribution’ and 1 measure of ‘entropy’. Due to certain limitations of these extraction methods there was a relative failure of network extraction in certain urban regions con- taining narrow and dense road structures. This loss of information was circumvented by segmenting the urban regions and computing a second set of geometrical and topological features from them. A set of 4 urban region features were computed and were categorized into 3 groups as follows: 2 measures of ‘density’, 1 measure of ‘labels’ and 1 measure of ‘compactness’. The 500 images (each of size 512x512 pixels) forming our database were selected from SPOT5 scenes with 5m resolution. From each image a set of geometrical and topological features were computed from the road networks and urban regions. These features were then used to classify the pre-defined geographical classes. Feature selection was done to avoid the burden of feature dimensionality and increase the classification performance. A set of 20 features was selected from 36 features by Fisher Linear Discriminant (FLD) analysis which gave the least classification error with an one-vs-rest linear Support Vector Machine (SVM). The impact of spatial resolution and size of images on the feature set have been explored in this work. We took a closer look at the effect of spatial resolution and size of images on the discriminative power of the feature set to classify the images belonging to the pre-defined geographical classes. Tests were performed with feature selection by FLD and one-vs-rest linear SVM classification on a database with images of 10m resolution. Another test was performed with feature selection by FLD and one-vs-rest linear SVM classification on a database with 5m resolution images (each of size 256x256 pixels). With the above mentioned approaches, we developed a novel method to classify large satellite images acquired by SPOT5 satellite (5m resolution) with patches of images each of size 512x512 pixels extracted from them. There has been a large amount of work dedicated to the classification of large satellite images at pixel level rather than considering image patches of different sizes. Classification of image patches of different sizes from a large satellite image is a novel idea in the sense that the patches considered contain significant coverage of a particular type of geographical environment. Road networks and urban region features were computed from these image patches extracted from the large image. A one-vs-rest Gaussian kernel SVM classification method was used to classify this large image. The classification results show that the image patches were labeled with the class having the maximum geographical coverage of the area associated in the large image. The large image was mapped into a “region matrix”, where each element of the matrix corresponds to a geographical class. This is a ‘hard’ classification and no inference can be drawn about the classification confidence. In certain cases, this produces some anomalies, as a single patch may contain two or more different geographical coverages. In order to have an estimate of these partial coverages, the output of the SVM was mapped into probabilities. These probability measures were then studied to have a closer look at the classification accuracies. The results confirm that our method is able to classify a large image into various geographical classes with a mean error of less than 10%. Future studies can use operators to detect not only man-made structures like roads and urban areas, but also natural entities like rivers, forests, etc. In this work we have restricted ourselves to a single resolution, but our methodology can be adapted to consider images of higher resolutions from QuickBird and the future Pleiade satellite. At a better resolution it may be possible to extract different structures like buildings, gardens, cross-roads, etc. This in turn will allow us to incorporate more classes to appropriately classify any geographical environment. At an image resolution of 1m, we may imagine to have sub-classes of an existing class, e.g., classes like urban Europe and urban USA can de divided into downtown, residential and industrial classes.

28 - 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 = {} }

29 - 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 = {} }

30 - AUTOMATIC FLAMINGO DETECTION USING A MULTIPLE BIRTH AND DEATH PROCESS. S. Descamps and X. Descombes and A. Béchet and J. Zerubia. In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Las Vegas, USA, March 2008. Copyright : copyright IEEE 2008 @INPROCEEDINGS{descamps08, author = {Descamps, S. and Descombes, X. and Béchet, A. and Zerubia, J.}, title = {AUTOMATIC FLAMINGO DETECTION USING A MULTIPLE BIRTH AND DEATH PROCESS}, year = {2008}, month = {March}, booktitle = {Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, address = {Las Vegas, USA}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2008_descamps08.pdf}, keyword = {} }

31 - Mixing Geometric and Radiometric Features for Change Classification. A. Fournier and X. Descombes and J. Zerubia. In Proc. SPIE Symposium on Electronic Imaging, San Jose, USA, January 2008. Keywords : Change detection, directional Statistics, polygonal approximation, Classification. Copyright : Copyright 2008 SPIE and IS&T. This paper was published in the proceedings of IS&T/SPIE 20th Annual Symposium on Electronic Imaging and is made available as an electronic reprint (preprint) with permission of SPIE and IS&T. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. @INPROCEEDINGS{fournier_spie08, author = {Fournier, A. and Descombes, X. and Zerubia, J.}, title = {Mixing Geometric and Radiometric Features for Change Classification}, year = {2008}, month = {January}, booktitle = {Proc. SPIE Symposium on Electronic Imaging}, address = {San Jose, USA}, url = {http://hal.inria.fr/inria-00269853/fr/}, keyword = {Change detection, directional Statistics, polygonal approximation, Classification} } Abstract : Most basic change detection algorithms use a pixel-based approach. Whereas such approach is quite well defined for monitoring important area changes (such as urban growth monitoring) in low resolution images, an object based approach seems more relevant when the change detection is specifically aimed toward targets (such as small buildings and vehicles). In this paper, we present an approach that mixes radiometric and geometric features to qualify the changed zones. The goal is to establish bounds (appearance, disappearance, substitution ...) between the detected changes and the underlying objects. We proceed by first clustering the change map (containing each pixel bitemporal radiosity) in different classes using the entropy-kmeans algorithm. Assuming that most man-made objects have a polygonal shape, a polygonal approximation algorithm is then used in order to characterize the resulting zone shapes. Hence allowing us to refine the primary rough classification, by integrating the polygon orientations in the state space. Tests are currently conducted on Quickbird data.

32 - 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} }

33 - 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} }

34 - Apprentissage non supervisé des SVM par un algorithme des K-moyennes entropique pour la détection de zones brûlées. O. Zammit and X. Descombes and J. Zerubia. In Proc. GRETSI Symposium on Signal and Image Processing, Troyes, France, September 2007. Keywords : Satellite images, Forest fires, Burnt areas, Classification, Support Vector Machines, Learning base. @INPROCEEDINGS{zammit_gretsi_07, author = {Zammit, O. and Descombes, X. and Zerubia, J.}, title = {Apprentissage non supervisé des SVM par un algorithme des K-moyennes entropique pour la détection de zones brûlées}, year = {2007}, month = {September}, booktitle = {Proc. GRETSI Symposium on Signal and Image Processing}, address = {Troyes, France}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2007_zammit_gretsi_07.pdf}, keyword = {Satellite images, Forest fires, Burnt areas, Classification, Support Vector Machines, Learning base} }

35 - Assessment of different classification algorithms for burnt land discrimination. O. Zammit and X. Descombes and J. Zerubia. In Proc. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pages 3000-3003, Barcelone, Spain, July 2007. Keywords : Satellite images, Burnt areas, Support Vector Machines, Forest fires, Classification. Copyright : IEEE @INPROCEEDINGS{zammit_igarss_07, author = {Zammit, O. and Descombes, X. and Zerubia, J.}, title = {Assessment of different classification algorithms for burnt land discrimination}, year = {2007}, month = {July}, booktitle = {Proc. IEEE International Geoscience and Remote Sensing Symposium (IGARSS)}, pages = {3000-3003}, address = {Barcelone, Spain}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4423476}, keyword = {Satellite images, Burnt areas, Support Vector Machines, Forest fires, Classification} }

36 - 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.

37 - Image deconvolution using a stochastic differential equation approach. X. Descombes and M. Lebellego and E. Zhizhina. In Proc. nternational Conference on Computer Vision Theory and Applications, Barcelona, Spain, March 2007. Keywords : Deconvolution, Stochastic Differential Equation. @INPROCEEDINGS{xavBarca2, author = {Descombes, X. and Lebellego, M. and Zhizhina, E.}, title = {Image deconvolution using a stochastic differential equation approach}, year = {2007}, month = {March}, booktitle = {Proc. nternational Conference on Computer Vision Theory and Applications}, address = {Barcelona, Spain}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2007_xavBarca2.pdf}, keyword = {Deconvolution, Stochastic Differential Equation} }

38 - Gap Filling in 3D Vessel like Patterns with Tensor Fields. L. Risser and F. Plouraboue and X. Descombes. In Proc. International Conference on Computer Vision Theory and Applications, 2007. Keywords : tensor voting, vascular network. @INPROCEEDINGS{XDbarca1, author = {Risser, L. and Plouraboue, F. and Descombes, X.}, title = {Gap Filling in 3D Vessel like Patterns with Tensor Fields}, year = {2007}, booktitle = {Proc. International Conference on Computer Vision Theory and Applications}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2007_XDbarca1.pdf}, keyword = {tensor voting, vascular network} }

39 - Vers une détection et une classification non-supervisées des changements inter-images. A. Fournier and X. Descombes and J. Zerubia. In Proc. Traitement et Analyse de l'Information - Méthodes et Applications (TAIMA), 2007. Keywords : Markov Random Fields, Registration, Change detection, Clustering. @INPROCEEDINGS{fournier-taima-07, author = {Fournier, A. and Descombes, X. and Zerubia, J.}, title = {Vers une détection et une classification non-supervisées des changements inter-images}, year = {2007}, booktitle = {Proc. Traitement et Analyse de l'Information - Méthodes et Applications (TAIMA)}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2007_fournier-taima-07.pdf}, keyword = {Markov Random Fields, Registration, Change detection, Clustering} }

40 - Use of ant colony optimization for finding neighbourhoods in non-stationary Markov random field models. S. Le Hegarat-Mascle and A. Kallel and X. Descombes. In Pattern Recognition and Machine Intelligence (PReMI'07), 2007. Keywords : Ants colonization, Markov Random Fields. @INPROCEEDINGS{ant07b, author = {Le Hegarat-Mascle, S. and Kallel, A. and Descombes, X.}, title = {Use of ant colony optimization for finding neighbourhoods in non-stationary Markov random field models}, year = {2007}, booktitle = {Pattern Recognition and Machine Intelligence (PReMI'07)}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2007_ant07b.pdf}, keyword = {Ants colonization, Markov Random Fields} }

41 - Tree Species Classification Using Radiometry, Texture and Shape Based Features. M. S. Kulikova and M. Mani and A. Srivastava and X. Descombes and J. Zerubia. In Proc. European Signal Processing Conference (EUSIPCO), 2007. Keywords : shape based features, SVM, tree classification. @INPROCEEDINGS{Kulikova07, author = {Kulikova, M. S. and Mani, M. and Srivastava, A. and Descombes, X. and Zerubia, J.}, title = {Tree Species Classification Using Radiometry, Texture and Shape Based Features}, year = {2007}, booktitle = {Proc. European Signal Processing Conference (EUSIPCO)}, pdf = {http://hal.archives-ouvertes.fr/docs/00/46/55/05/PDF/Kulikova_EUSIPCO2007.pdf}, keyword = {shape based features, SVM, tree classification} } Abstract : We consider the problem of tree species classification from high resolution aerial images based on radiometry, texture and a shape modeling. We use the notion of shape space proposed by Klassen et al., which provides a shape description invariant to translation, rotation and scaling. The shape features are extracted within a geodesic distance in the shape space. We then perform a classification using a SVM approach. We are able to show that the shape descriptors improve the classification performance relative to a classifier based on radiometric and textural descriptors alone. We obtain these results using high resolution Colour InfraRed (CIR) aerial images provided by the Swedish University of Agricultural Sciences. The image viewpoint is close to the nadir, i.e. the tree crowns are seen from above.

42 - Burnt area mapping using Support Vector Machines. O. Zammit and X. Descombes and J. Zerubia. In Proc. International Conference on Forest Fire Research, Figueira da Foz, Portugal, November 2006. Keywords : Satellite images, Forest fires, Burnt areas, Support Vector Machines. @INPROCEEDINGS{zammit_icffr_06, author = {Zammit, O. and Descombes, X. and Zerubia, J.}, title = {Burnt area mapping using Support Vector Machines}, year = {2006}, month = {November}, booktitle = {Proc. International Conference on Forest Fire Research}, address = {Figueira da Foz, Portugal}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2006_zammit_icffr_06.pdf}, keyword = {Satellite images, Forest fires, Burnt areas, Support Vector Machines} }

43 - 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} }

44 - Computing statistics from a graph representation of road networks in satellite images for indexing and retrieval. A. Bhattacharya and I. H. Jermyn and X. Descombes and J. Zerubia. In Proc. compImage, Coimbra, Portugal, October 2006. Keywords : Road network, Indexation, Semantic, Retrieval, Feature statistics. @INPROCEEDINGS{bhatta_compimage06, author = {Bhattacharya, A. and Jermyn, I. H. and Descombes, X. and Zerubia, J.}, title = {Computing statistics from a graph representation of road networks in satellite images for indexing and retrieval}, year = {2006}, month = {October}, booktitle = {Proc. compImage}, address = {Coimbra, Portugal}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2006_bhatta_compimage06.pdf}, keyword = {Road network, Indexation, Semantic, Retrieval, Feature statistics} } Abstract : Retrieval from remote sensing image archives relies on the extraction of pertinent information from the data about the entity of interest (e.g. land cover type), and on the robustness of this extraction to nuisance variables (e.g. illumination). Most image-based characterizations are not invariant to such variables. However, other semantic entities in the image may be strongly correlated with the entity of interest and their properties can therefore be used to characterize this entity. Road networks are one example: their properties vary considerably, for example, from urban to rural areas. This paper takes the first steps towards classification (and hence retrieval) based on this idea. We study the dependence of a number of network features on the class of the image ('urban' or 'rural'). The chosen features include measures of the network density, connectedness, and `curviness'. The feature distributions of the two classes are well separated in feature space, thus providing a basis for retrieval. Classification using kernel k-means confirms this conclusion.

45 - 2D and 3D Vegetation Resource Parameters Assessment using Marked Point Processes. G. Perrin and X. Descombes and J. Zerubia. In Proc. International Conference on Pattern Recognition (ICPR), Hong-Kong, August 2006. Keywords : Data energy, Object extraction, Tree Crown Extraction, Stochastic geometry, Marked point process. @INPROCEEDINGS{perrin_06_c, author = {Perrin, G. and Descombes, X. and Zerubia, J.}, title = {2D and 3D Vegetation Resource Parameters Assessment using Marked Point Processes}, year = {2006}, month = {August}, booktitle = {Proc. International Conference on Pattern Recognition (ICPR)}, address = {Hong-Kong}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2006_perrin_06_c.pdf}, keyword = {Data energy, Object extraction, Tree Crown Extraction, Stochastic geometry, Marked point process} } Abstract : High resolution aerial and satellite images of forests have a key role to play in natural resource management. As they enable to study forests at the scale of trees, it is now possible to get a more accurate evaluation of the forest resources, from which can be deduced information of biodiversity and ecological sustainability. In that prospect, automatic algorithms are needed to give a further exploitation of the data and to assist human operators. In this paper, we present a stochastic geometry approach to extract 2D and 3D parameters of the trees, by modelling the stands as some realizations of a marked point process of ellipses or ellipsoids, whose points are the positions of the trees and marks their geometric features. This approach gives also the number of stems, their position, and their size. It is an energy minimization problem, where the energy embeds a regularization term (prior density), which introduces some interactions between the objects, and a data term, which links the objects to the features to be extracted. Results are shown on aerial images provided by the French National Forest Inventory (IFN).

46 - 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} }

47 - A comparative study of three methods for identifying individual tree crowns in aerial images covering different types of forests. M. Eriksson and G. Perrin and X. Descombes and J. Zerubia. In Proc. International Society for Photogrammetry and Remote Sensing (ISPRS), Marne La Vallee, France, July 2006. Keywords : Region Growing, Marked point process, Markov Fields, Object extraction, Tree Crown Extraction. @INPROCEEDINGS{eriksson06a, author = {Eriksson, M. and Perrin, G. and Descombes, X. and Zerubia, J.}, title = {A comparative study of three methods for identifying individual tree crowns in aerial images covering different types of forests}, year = {2006}, month = {July}, booktitle = {Proc. International Society for Photogrammetry and Remote Sensing (ISPRS)}, address = {Marne La Vallee, France}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2006_eriksson06a.pdf}, keyword = {Region Growing, Marked point process, Markov Fields, Object extraction, Tree Crown Extraction} } Abstract : Most of today's silviculture methods has the goal to optimise the outcome of the forest in stem volume when it is cut.‭ ‬It might also be relevant to save parts of the forest,‭ ‬for instance,‭ ‬to protect a habitat.‭ ‬In order to get a good survey of the forest,‭ ‬remote sensed images are often used.‭ ‬These images are most often manually interpreted in combination with field measurements in order to estimate the forest parameters that are of importance in the decision how to optimally maintain the forest.‭ ‬Among these parameters the most common are stem number,‭ ‬stem volume,‭ ‬and tree species.‭ ‬Interpretation of images are often labour and time consuming.‭ ‬Thus,‭ ‬automatically developed methods for interpretation can lower the work load and speed up the interpretation time.‭ The interpretation is often done using images captured from a far distance from the ground in order to capture as large area as possible.‭ ‬However,‭ ‬this lower the accuracy of the estimates since it must be done stand wise.‭ ‬Knowledge of where each individual trees in the forest is located together with its size will increase accuracy.‭ ‬It makes it also possible to plan the cutting in detail.‭ ‬With this knowledge in mind,‭ ‬research about finding automatically methods for finding individual tree crowns in aerial images has been a subject for researchers the last decades.‭ Today's methods are not capable to alone handle all kind of forests.‭ ‬Therefore,‭ ‬comparative studies of different segmentation methods with different types of forests are of importance in order to clarify how much a method is reliable at a certain type of forest.‭ ‬This knowledge can,‭ ‬for instance,‭ ‬be used to build up an expert system which are supposed to be able to find individual tree crowns in any kind of forests.‭ ‬The comparison is done using images covering different types of forests.‭ ‬The types of forests that are included in the study ranges from isolated tree crown where the ground is clearly visible between the crowns to dense forest which is naturally regenerated via planted forest. In this study we compare three existing segmentation methods for extracting individual tree crowns from aerial images.‭ ‬The first two methods are probabilistic methods which minimises some energy function while the third is a region growing algorithm.‭ ‬The first probabilistic method is based on a Markov Random Field modelling.‭ ‬We define a prior Markov model to segment the image into three classes‭ (‬background,‭ ‬vegetation and tree centres‭)‬.‭ ‬The prior model embed a circular shape model of the tree crown with a‭ ‬random radius.‭ ‬The data term allows to well position the tree centres onto the image and to describe the tree shape as fluctuations around the circular template.‭ ‬Besides,‭ ‬some long range interactions models the relations between the trees locations,‭ ‬such as some periodicity in case of plantations.‭ The second probabilistic method consists in modeling the trees in the forestry images as random configurations of ellipses or ellipsoids,‭ ‬whose points are the positions of the stems and marks their geometric features.‭ ‬The density of this process embeds a regularization term‭ (‬prior density‭)‬,‭ ‬which introduces some interactions between the objects,‭ ‬and a data term,‭ ‬which links the objects to the features to be extracted.‭ ‬We estimate the best configuration of an unknown number of objects,‭ ‬from which‭ ‬2D and‭ ‬3D vegetation resource parameters can be extracted.‭ ‬To sample this marked point process,‭ ‬we use Monte Carlo dynamics,‭ ‬while the optimization is performed via a Simulated Annealing algorithm,‭ ‬which results in a fully automatic approach.‭ ‬This approach works well on plantations,‭ ‬where there are high spatial relations between the trees,‭ ‬and on isolated trees where‭ ‬3D parameters can be extracted,‭ ‬but some difficulties remain in dense areas.‭ The third method,‭ ‬the region growing algorithm,‭ ‬relies as all region growing methods on good seed points,‭ ‬i.e.‭ ‬in this case approximate locations of the tree crowns.‭ ‬From the seed points the segments are grown according to a grey level value of the neighbouring pixels.‭ ‬The larger the value is the sooner it is connected to the neighbouring segment.‭ ‬The segments stops to grow when all pixels belongs to a segment.‭ ‬This method,‭ ‬contrary the others,‭ ‬will have as a result,‭ ‬segments that have captured the actual shape of the tree crown if the forest is not too sparse.‭ ‬If the forest is too sparse such that the ground is visible,‭ ‬there are problems of finding the seed points.‭ ‬In the cases when the forest is sparse,‭ ‬there are difficulties to separate the tree crowns from the ground.‭ ‬Even if the seed points would be located only at the tree crowns the result will contain a lot of errors since all pixels most belong to a segment,‭ ‬i.e.‭ ‬even the ground pixels must be connected to a segment in this case.‭

48 - 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)} }

49 - Forest Resource Assessment using Stochastic Geometry. G. Perrin and X. Descombes and J. Zerubia and J.G. Boureau. In Proc. International Precision Forestry Symposium, March 2006. Keywords : Tree Crown Extraction, Object extraction, Stochastic geometry, RJMCMC, Data energy. @INPROCEEDINGS{perrin_06_b, author = {Perrin, G. and Descombes, X. and Zerubia, J. and Boureau, J.G.}, title = {Forest Resource Assessment using Stochastic Geometry}, year = {2006}, month = {March}, booktitle = {Proc. International Precision Forestry Symposium}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/perrin_ipfs06.pdf}, keyword = {Tree Crown Extraction, Object extraction, Stochastic geometry, RJMCMC, Data energy} } Abstract : Aerial and satellite imagery has a key role to play in natural resource management, especially in forestry application. The submetric resolution of the data enables to study forests at the scale of trees, and to get a more accurate assessment of the resources such as the number of stems or the forest cover. To develop automatic tools in order to help the inventories in their work and to bring more knowledge about the stands is also nowadays of important economical and environmental concerns. In this paper, we aim at extracting tree crowns from high resolution aerial Color Infrared images (CIR) of forests using marked point processes. Our approach consists in modelling the trees in the forestry images as random configurations of ellipses, whose points are the positions of the stems and marks their geometric features. The density of this process embeds a regularization term (prior density), which introduces some interactions between the objects, and a data term, which links the objects to the features to be extracted. Our goal is to find the best configuration of an unknown number of objects, i.e. the configuration that maximizes this density. To sample this marked point process, we use Monte Carlo dynamics while the optimization is performed via a Simulated Annealing algorithm, which results in a fully automatic approach. We present different models for the data term in order to cope with different kinds of stands : plantations, isolated trees and mixed stands. Results are shown on aerial CIR images provided by the French Forest Inventory (IFN)

50 - Evaluation des Ressources Forestières à l'aide de Processus Ponctuels Marqués. G. Perrin and X. Descombes and J. Zerubia. In Proc. Reconnaissance des Formes et Intelligence Artificielle (RFIA), Tours, France, January 2006. Keywords : Tree Crown Extraction, Stochastic geometry, Marked point process, Object extraction. @INPROCEEDINGS{perrin_06_a, author = {Perrin, G. and Descombes, X. and Zerubia, J.}, title = {Evaluation des Ressources Forestières à l'aide de Processus Ponctuels Marqués}, year = {2006}, month = {January}, booktitle = {Proc. Reconnaissance des Formes et Intelligence Artificielle (RFIA)}, address = {Tours, France}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/perrin_rfia06.pdf}, keyword = {Tree Crown Extraction, Stochastic geometry, Marked point process, Object extraction} } Résumé : Les images aériennes et satellitaires jouent un role de plus en plus important dans le domaine de la gestion des ressources naturelles, et en particulier des forêts. Les organismes chargés d'en faire l'inventaire, comme l'Inventaire Forestier National (IFN) en France, s'appuient en effet sur ces images pour observer les différentes espèces d'arbres d'une zone boisée, avant de se rendre sur le terrain pour une étude plus poussée. La résolution submétrique des données permet, en outre, d'entrevoir une étude plus fine, à savoir un comptage à l'arbre près et une classification automatique des houppiers (ensemble des branches et du feuillage d'un arbre). Cette évaluation précise des ressources forestières n'est actuellement pas disponible. Aussi, le développement d'outils automatiques, chargés d'aider les gestionnaires du paysage dans leur travail en leur apportant une connaissance des ressources à l'échelle de l'arbre, se révèle-t-il être d'un intérêt grandissant.L'objectif de notre travail est donc d'extraire des houppiers à partir d'images aériennes de forêts à très haute résolution. Notre approche consiste à modéliser les peuplements forestiers par un processus ponctuel marqué d'ellipses, dont les points représentent les positions des arbres et les marques leurs caractéristiques géométriques. La densité de ce processus comporte une composante de régularisation, dite a priori, qui introduit des interactions entre les objets du processus, ainsi qu'une composante d'attache aux données, afin que les objets du processus se positionnent sur les houppiers que l'on souhaite extraire. Il s'agit de trouver la configuration d'objets, en nombre inconnu a priori, qui maximise cette densité. La simulation de tels processus fait appel aux algorithmes de type Monte Carlo par Chaîne de Markov (MCMC) à sauts réversibles, l'optimisation étant réalisée à l'aide d'un recuit simulé.Nous présentons ici un nouveau modèle d'attache aux données. Contrairement à nos précédents modèles testés sur des plantations, ce modèle n'est plus bayésien puisque le terme d'attache aux données est désormais calculé au niveau des objets et non de l'image. Ceci nous permet de travailler sur des images plus générales, avec des densités d'arbres plus variables. Des résultats obtenus sur des images fournies par l'IFN valident ce modèle. Abstract : Aerial and satellite imagery has a key role to play in natural resources management, especially in forestry application. Indeed, forest inventories, such as the French National Inventory (IFN), refer to these images to analyse the different tree species in a stand, before sending a team on the ground to obtain some more advanced knowledge. Moreover, the submetric resolution of the data enables to study forests at the scale of trees, and also to get a more accurate evaluation of the resources such as the number of stems. It would be also of important economical and environmental concerns to develop automatic tools to analyze and monitor forests.We aim at extracting tree crowns from high resolution aerial images of forests. Our approach consists in modelling the forestry images as realizations of a marked point process of ellipses, whose points are the positions of the trees and marks their geometric features. The density of this process embeds a regularization term (prior density), which introduces some interactions between the objects, and a data term, which links the objects to the features to be extracted. Our goal is to find the best configuration of an unknown number of objects, i.e. the configuration that maximizes this density. To sample the marked point process, we use Monte Carlo dynamics (Reversible Jump Markov Chain Monte Carlo), while the optimization is performed via a simulated annealing algorithm.We present here a new model for the data term. Contrary to our previous models tested on plantations images, this model is not Bayesian anymore : the data term is calculated for each object and not for the whole image. This enables us to work on more general images, with variable tree crown densities. Example results are shown on aerial images provided by the French Forest Inventory (IFN).

51 - Galaxy filament detection using the Quality candy model. P. Gernez and X. Descombes and J. Zerubia and E. Slezak and A. Bijaoui. In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2006. Keywords : Marked point process, Quality Candy model, Galaxy Filaments. @INPROCEEDINGS{gernez06, author = {Gernez, P. and Descombes, X. and Zerubia, J. and Slezak, E. and Bijaoui, A.}, title = {Galaxy filament detection using the Quality candy model}, year = {2006}, booktitle = {Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2006_gernez06.pdf}, keyword = {Marked point process, Quality Candy model, Galaxy Filaments} }

52 - Point process of segments and rectangles for building extraction from DEM. M. Ortner and X. Descombes and J. Zerubia. In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2006. Keywords : Stochastic geometry, Buildings. @INPROCEEDINGS{ortner06, author = {Ortner, M. and Descombes, X. and Zerubia, J.}, title = {Point process of segments and rectangles for building extraction from DEM}, year = {2006}, booktitle = {Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/2006_ortner06.pdf}, keyword = {Stochastic geometry, Buildings} }

53 - Adaptive Simulated Annealing for Energy Minimization Problem in a Marked Point Process Application. G. Perrin and X. Descombes and J. Zerubia. In Proc. Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), St Augustine, Florida, USA, November 2005. Keywords : Simulated Annealing, Marked point process, Stochastic geometry, MAP estimation, RJMCMC. Copyright : Springer Verlag @INPROCEEDINGS{perrin_emmcvpr05, author = {Perrin, G. and Descombes, X. and Zerubia, J.}, title = {Adaptive Simulated Annealing for Energy Minimization Problem in a Marked Point Process Application}, year = {2005}, month = {November}, booktitle = {Proc. Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR)}, address = {St Augustine, Florida, USA}, pdf = {ftp://ftp-sop.inria.fr/ariana/Articles/perrin_emmcvpr.pdf}, ps = {ftp://ftp-sop.inria.fr/ariana/Articles/perrin_emmcvpr.ps.gz}, keyword = {Simulated Annealing, Marked point process, Stochastic geometry, MAP estimation, RJMCMC} } Abstract : We use marked point processes to detect an unknown number of trees from high resolution aerial images. This is in fact an energy minimization problem, where the energy contains a prior term which takes into account the geometrical properties of the objects, and a data term to match these objects to the image. This stochastic process is simulated via a Reversible Jump Markov Chain Monte Carlo procedure, which embeds a Simulated Annealing scheme to extract the best configuration of objects. We compare here different cooling schedules of the Simulated Annealing algorithm which could provide some good minimization in a short time. We also study some adaptive proposition kernels.

54 - 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} }

55 - Extraction of hydrographic networks from satellite images using a hierarchical model within a stochastic geometry framework. C. Lacoste and X. Descombes and J. Zerubia and N. Baghdadi. In Proc. European Signal Processing Conference (EUSIPCO), Antalya, Turkey, September 2005. @INPROCEEDINGS{lacoste_eusipco05, author = {Lacoste, C. and Descombes, X. and Zerubia, J. and Baghdadi, N.}, title = {Extraction of hydrographic networks from satellite images using a hierarchical model within a stochastic geometry framework}, year = {2005}, month = {September}, booktitle = {Proc. European Signal Processing Conference (EUSIPCO)}, address = {Antalya, Turkey}, url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7078007}, keyword = {} }

top of the page

navigation : 1 - 2 - 3 - 4 display : 10 per page | 20 per page | 50 per page

These pages were generated by