|
|
Caroline Lacoste
Former PhD Student
 Keywords : Stochastic Geometry, MCMC, Object extraction, Line networks, Roads
 Demo : see this author's demo
 Contact :
|
| Last publications in Ariana Research Group :
Unsupervised line network extraction in remote sensing using a polyline process.
C. Lacoste and X. Descombes and J. Zerubia. Pattern Recognition, 43(4): pages 1631-1641, April 2010.
Keywords : Marked point process, Line networks, Road network extraction.
@ARTICLE{lacoste10,
|
| author |
= |
{Lacoste, C. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Unsupervised line network extraction in remote sensing using a polyline process}, |
| year |
= |
{2010}, |
| month |
= |
{April}, |
| journal |
= |
{Pattern Recognition}, |
| volume |
= |
{43}, |
| number |
= |
{4}, |
| pages |
= |
{1631-1641}, |
| url |
= |
{http://dx.doi.org/10.1016/j.patcog.2009.11.003}, |
| keyword |
= |
{Marked point process, Line networks, Road network extraction} |
| } |
Abstract :
Marked point processes provide a rigorous framework to describe a scene by an unordered set of objects. The efficiency of this modeling has been shown on line network extraction with models manipulating interacting segments. In this paper, we extend this previous modeling to polylines composed of an unknown number of segments. Optimization is done via simulated annealing using a Reversible Jump Markov Chain Monte Carlo (RJMCMC) algorithm. We accelerate the convergence of the algorithm by using appropriate proposal kernels. Results on aerial and satellite images show that this new model outperforms the previous one. |
Point Processes for Unsupervised Line Network Extraction in Remote Sensing.
C. Lacoste and X. Descombes and J. Zerubia. IEEE Trans. Pattern Analysis and Machine Intelligence, 27(10): pages 1568-1579, October 2005.
@ARTICLE{lacoste05,
|
| author |
= |
{Lacoste, C. and Descombes, X. and Zerubia, J.}, |
| title |
= |
{Point Processes for Unsupervised Line Network Extraction in Remote Sensing}, |
| year |
= |
{2005}, |
| month |
= |
{October}, |
| journal |
= |
{IEEE Trans. Pattern Analysis and Machine Intelligence}, |
| volume |
= |
{27}, |
| number |
= |
{10}, |
| pages |
= |
{1568-1579}, |
| pdf |
= |
{http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=32189&arnumber=1498752&count=18&index=4}, |
| keyword |
= |
{} |
| } |
Hydrographic Network Extraction from Radar Satellite Imagesusing a Hierarchical Model within a Stochastic Geometry Framework.
C. Lacoste and X. Descombes and J. Zerubia and N. Baghdadi. Research Report 5697, INRIA, France, September 2005.
@TECHREPORT{rrHimne,
|
| author |
= |
{Lacoste, C. and Descombes, X. and Zerubia, J. and Baghdadi, N.}, |
| title |
= |
{Hydrographic Network Extraction from Radar Satellite Imagesusing a Hierarchical Model within a Stochastic Geometry Framework}, |
| year |
= |
{2005}, |
| month |
= |
{September}, |
| institution |
= |
{INRIA}, |
| type |
= |
{Research Report}, |
| number |
= |
{5697}, |
| address |
= |
{France}, |
| url |
= |
{http://hal.inria.fr/inria-00070318}, |
| pdf |
= |
{http://hal.inria.fr/docs/00/07/03/18/PDF/RR-5697.pdf}, |
| keyword |
= |
{} |
| } |
Résumé :
Ce rapport présente un algorithme d'extraction non supervisée de réseaux hydrographiques à partir d'images satellitaires exploitant la structure arborescante de tels réseaux. L'extraction du surfacique (branches de largeur supérieure à trois pixels) est réalisée par un algorithme efficace fondé sur une modélisation par champ de Markov. Ensuite, l'extraction du linéique se fait par un algorithme récursif fondé sur un modèle hiérarchique dans lequel les affluents d'un fleuve donné sont modélisés par un processus ponctuel marqué défini dans le voisinage de ce fleuve. L'optimisation de chaque processus ponctuel est réalisée par un recuit simulé utilisant un algorithme de Monte Carlo par chaîne de Markov à sauts réversibles. Nous obtenons de bons résultats en terme d'omissions et de surdétections sur une image radar de type ERS. |
Abstract :
This report presents a two-step algorithm for unsupervised extraction of hydrographic networks from satellite images, that exploits the tree structures of such networks. First, the thick branches of the network are detected by an efficient algorithm based on a Markov random field. Second, the line branches are extracted using a recursive algorithm based on a hierarchical model of the hydrographic network, in which the tributaries of a given river are modeled by an object process (or a marked point process) defined within the neighborhood of this river. Optimization of each point process is done via simulated annealing using a reversible jump Markov chain Monte Carlo algorithm. We obtain encouraging results in terms of omissions and overdetections on a radar satellite image. |
|
All publications in Ariana Research Group
|
|
New demo webpage
