Centre de documentation
scientifique

Fully convolutional neural network for impervious surface segmentation in mixed urban environment / Joseph McGlinchy in Photogrammetric Engineering & Remote Sensing, PERS, vol 87 n° 2 (February 2021)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 87 n° 2 (February 2021) . - pp 117 - 123 Titre : Fully convolutional neural network for impervious surface segmentation in mixed urban environment Type de document : Article/Communication Auteurs : Joseph McGlinchy, Auteur ; Brian Muller, Auteur ; Brian Johnson, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 117 - 123 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] croissance urbaine [Termes IGN] Denver [Termes IGN] exactitude des données [Termes IGN] image multibande [Termes IGN] image Worldview [Termes IGN] milieu urbain [Termes IGN] segmentation [Termes IGN] surface imperméable Résumé : (Auteur) The urgency of creating appropriate, high-resolution data products such as impervious cover information has increased as cities face rapid growth as well as climate change and other environmental challenges. This work explores the use of fully convolutional neural networks (FCNNs )—specifically UNet with a ResNet-152 encoder—in mapping impervious surfaces at the pixel level from WorldView-2 in a mixed urban/residential environment. We investigate three-, four-, and eight-band multispectral inputs to the FCNN. Resulting maps are promising in both qualitative and quantitative assessment when compared to automated land use/land cover products. Accuracy was assessed by F1 and average precision (AP) scores, as well as receiver operating characteristic curves, with area under the curve (AUC ) used as an additional accuracy metric. The four-band model shows the highest average test-set accuracies (F1, AP, and AUC of 0.709, 0.82, and 0.807, respectively), with higher AP and AUC than the automated land use/land cover products, indicating the utility of the blue-green-red-infrared channels for the FCNN. Improved performance was seen in residential areas, with worse performance in more densely developed areas. Numéro de notice : A2021-099 Affiliation des auteurs : non IGN Thématique : IMAGERIE/URBANISME Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.87.2.117 Date de publication en ligne : 01/02/2021 En ligne : https://doi.org/10.14358/PERS.87.2.117 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97045 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2021021	SL	Revue	Centre de documentation	Revues en salle	Disponible