HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Reports

Hydrographic Network Extraction from Radar Satellite Images using a Hierarchical Model within a Stochastic Geometry Framework

Caroline Lacoste 1 Xavier Descombes 1 Josiane Zerubia 1 Nicolas Baghdadi 1
1 ARIANA - Inverse problems in earth monitoring
CRISAM - Inria Sophia Antipolis - Méditerranée , Laboratoire I3S - SIS - Signal, Images et Systèmes
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.
Document type :
Reports
Complete list of metadata

Cited literature [1 references]  Display  Hide  Download

https://hal.inria.fr/inria-00070318
Contributor : Rapport de Recherche Inria Connect in order to contact the contributor
Submitted on : Friday, May 19, 2006 - 8:03:23 PM
Last modification on : Friday, February 4, 2022 - 3:21:53 AM
Long-term archiving on: : Sunday, April 4, 2010 - 8:55:46 PM

Identifiers

  • HAL Id : inria-00070318, version 1

Collections

Citation

Caroline Lacoste, Xavier Descombes, Josiane Zerubia, Nicolas Baghdadi. Hydrographic Network Extraction from Radar Satellite Images using a Hierarchical Model within a Stochastic Geometry Framework. [Research Report] RR-5697, INRIA. 2006, pp.27. ⟨inria-00070318⟩

Share

Metrics

Record views

160

Files downloads

187