Skip to Main content Skip to Navigation
Conference papers

Assessment of road extraction methods from satellite images : reflections and case study on the definition of a reference

Abstract : In the context of an automatic street extraction algorithm from remotely sensed images, we are concerned about defining some quantitative criteria for evaluating the performance of our method. The aim is to obtain quality measures of the results delivered by a method. This purpose needs the definition of a reference in order to compare it with extracted objects. In this paper, existing references in matter of road extraction from geographical scenes are reviewed. Then a methodology for defining a reference is proposed. The complete methodology is applied on a high resolution image from the IKONOS satellite. Conclusions are drawn enhancing the benefits of such an approach and future prospects are discussed.
Document type :
Conference papers
Complete list of metadata

https://hal-mines-paristech.archives-ouvertes.fr/hal-00534259
Contributor : Corinne Matarasso <>
Submitted on : Tuesday, November 9, 2010 - 11:03:20 AM
Last modification on : Thursday, September 24, 2020 - 5:22:03 PM

Identifiers

  • HAL Id : hal-00534259, version 1

Citation

Renaud Peteri, Thierry Ranchin. Assessment of road extraction methods from satellite images : reflections and case study on the definition of a reference. 22nd symposium of the EARSel Laboratories : GEOINFORMATION FOR EUROPEAN-WIDE INTEGRATION, Jun 2002, Prague, Czech Republic. p.141-147 - 90-77017-71-2. ⟨hal-00534259⟩

Share

Metrics

Record views

114