Centre de documentation
scientifique

A deep learning approach to DTM extraction from imagery using rule-based training labels / Caroline M. Gevaert in ISPRS Journal of photogrammetry and remote sensing, vol 142 (August 2018)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 142 (August 2018) . - pp 106 - 123 Titre : A deep learning approach to DTM extraction from imagery using rule-based training labels Type de document : Article/Communication Auteurs : Caroline M. Gevaert, Auteur ; Claudio Persello, Auteur ; M. George Vosselman, Auteur Année de publication : 2018 Article en page(s) : pp 106 - 123 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] base de règles [Termes IGN] benchmark spatial [Termes IGN] Dar-es-Salam (Tanzanie) [Termes IGN] drone [Termes IGN] échantillonnage d'image [Termes IGN] extraction automatique [Termes IGN] Kigali (Rwanda) [Termes IGN] Lombardie [Termes IGN] modèle numérique de terrain [Termes IGN] photogrammétrie aérienne [Termes IGN] réseau neuronal convolutif Résumé : (Auteur) Existing algorithms for Digital Terrain Model (DTM) extraction still face difficulties due to data outliers and geometric ambiguities in the scene such as contiguous off-ground areas or sloped environments. We postulate that in such challenging cases, the radiometric information contained in aerial imagery may be leveraged to distinguish between ground and off-ground objects. We propose a method for DTM extraction from imagery which first applies morphological filters to the Digital Surface Model to obtain candidate ground and off-ground training samples. These samples are used to train a Fully Convolutional Network (FCN) in the second step, which can then be used to identify ground samples for the entire dataset. The proposed method harnesses the power of state-of-the-art deep learning methods, while showing how they can be adapted to the application of DTM extraction by (i) automatically selecting and labelling dataset-specific samples which can be used to train the network, and (ii) adapting the network architecture to consider a larger surface area without unnecessarily increasing the computational burden. The method is successfully tested on four datasets, indicating that the automatic labelling strategy can achieve an accuracy which is comparable to the use of manually labelled training samples. Furthermore, we demonstrate that the proposed method outperforms two reference DTM extraction algorithms in challenging areas. Numéro de notice : A2018-298 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2018.06.001 Date de publication en ligne : 15/06/2018 En ligne : https://doi.org/10.1016/j.isprsjprs.2018.06.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90410 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2018081	RAB	Revue	Centre de documentation	En réserve L003	Disponible
081-2018083	DEP-EXM	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2018082	DEP-EAF	Revue	Nancy	Dépôt en unité	Exclu du prêt