inscription
PORTAIL D'INFORMATION GÉOGRAPHIQUE

Advances in automated detection of sand dunes on Mars

Auteur(s) et Affiliation(s)

BANDEIRA, L.
CERENA-Centro de Recursos Naturais e Ambiente, Inst. Sup. Técnico, Lisboa, Portugal
MARQUES, J.S.
ISR - Inst. de Sistemas e Robótica, Inst. Sup. Técnico, Lisboa, Portugal
SARAIVA, J.
CERENA-Centro de Recursos Naturais e Ambiente, Inst. Sup. Técnico, Lisboa, Portugal
PINA, P.
CERENA-Centro de Recursos Naturais e Ambiente, Inst. Sup. Técnico, Lisboa, Portugal


Description :
This paper describes advances in an automatic approach for the detection of sand dunes of Mars, based on supervised learning techniques. A set of features (gradient histogram) is extracted from the remotely sensed images and 2 classifiers (Support Vector Machine and Random Forests) are trained from this data. The evaluation is conducted on 230 MOC-NA images (spatial resolution between 1.45 and 6.80 m/pixel) leading to about 89% of correct detections. A detailed analysis of the detection results (dune/non-dune) is performed by dune type or bulk shape, confirming high performances independently of the way the dataset is analysed. This demonstrates the robustness and adequacy of the automated approach to deal with the large variety of aeolian structures present on the surface of Mars.


Type de document :
Article de périodique

Source :
Earth surface processes and landforms, issn : 0197-9337, 2013, vol. 38, n°. 3, p. 275-283, nombre de pages : 9, Références bibliographiques : 16 ref.

Date :
2013

Editeur :
Pays édition : Royaume-Uni, Chichester, Wiley

Langue :
Anglais
Droits :
Tous droits réservés © Prodig - Bibliographie Géographique Internationale (BGI)