Centre de documentation
scientifique

Detection of windthrown tree stems on UAV-orthomosaics using U-Net convolutional networks / Stefan Reder in Remote sensing, vol 14 n° 1 (January-1 2022)  

Public [article]  inRemote sensing > vol 14 n° 1 (January-1 2022) . - n° 75 Titre : Detection of windthrown tree stems on UAV-orthomosaics using U-Net convolutional networks Type de document : Article/Communication Auteurs : Stefan Reder, Auteur ; J.P. Mund, Auteur ; Nicole Albert, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 75 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] branche (arbre) [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection d'objet [Termes IGN] dommage forestier causé par facteurs naturels [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] image captée par drone [Termes IGN] orthophotoplan numérique [Termes IGN] segmentation sémantique [Termes IGN] tempête [Termes IGN] tronc Résumé : (auteur) The increasing number of severe storm events is threatening European forests. Besides the primary damages directly caused by storms, there are secondary damages such as bark beetle outbreaks and tertiary damages due to negative effects on the market. These subsequent damages can be minimized if a detailed overview of the affected area and the amount of damaged wood can be obtained quickly and included in the planning of clearance measures. The present work utilizes UAV-orthophotos and an adaptation of the U-Net architecture for the semantic segmentation and localization of windthrown stems. The network was pre-trained with generic datasets, randomly combining stems and background samples in a copy–paste augmentation, and afterwards trained with a specific dataset of a particular windthrow. The models pre-trained with generic datasets containing 10, 50 and 100 augmentations per annotated windthrown stems achieved F1-scores of 73.9% (S1Mod10), 74.3% (S1Mod50) and 75.6% (S1Mod100), outperforming the baseline model (F1-score 72.6%), which was not pre-trained. These results emphasize the applicability of the method to correctly identify windthrown trees and suggest the collection of training samples from other tree species and windthrow areas to improve the ability to generalize. Further enhancements of the network architecture are considered to improve the classification performance and to minimize the calculative costs. Numéro de notice : A2022-082 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.3390/rs14010075 En ligne : https://doi.org/10.3390/rs14010075 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99476 [article]