Centre de documentation
scientifique

Exploring geo-tagged photos for land cover validation with deep learning / Hanfa Xing in ISPRS Journal of photogrammetry and remote sensing, vol 141 (July 2018)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 141 (July 2018) . - pp 237 - 251 Titre : Exploring geo-tagged photos for land cover validation with deep learning Type de document : Article/Communication Auteurs : Hanfa Xing, Auteur ; Yuan Meng, Auteur ; Zixuan Wang, Auteur ; Kaixuan Fan, Auteur ; Dongyang Hou, Auteur Année de publication : 2018 Article en page(s) : pp 237 - 251 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] apprentissage profond [Termes IGN] base de données d'occupation du sol [Termes IGN] Californie (Etats-Unis) [Termes IGN] échantillon [Termes IGN] estimation de précision [Termes IGN] géobalise [Termes IGN] image numérique [Termes IGN] occupation du sol [Termes IGN] production participative [Termes IGN] réseau neuronal convolutif Résumé : (Auteur) Land cover validation plays an important role in the process of generating and distributing land cover thematic maps, which is usually implemented by high cost of sample interpretation with remotely sensed images or field survey. With an increasing availability of geo-tagged landscape photos, the automatic photo recognition methodologies, e.g., deep learning, can be effectively utilised for land cover applications. However, they have hardly been utilised in validation processes, as challenges remain in sample selection and classification for highly heterogeneous photos. This study proposed an approach to employ geo-tagged photos for land cover validation by using the deep learning technology. The approach first identified photos automatically based on the VGG-16 network. Then, samples for validation were selected and further classified by considering photos distribution and classification probabilities. The implementations were conducted for the validation of the GlobeLand30 land cover product in a heterogeneous area, western California. Experimental results represented promises in land cover validation, given that GlobeLand30 showed an overall accuracy of 83.80% with classified samples, which was close to the validation result of 80.45% based on visual interpretation. Additionally, the performances of deep learning based on ResNet-50 and AlexNet were also quantified, revealing no substantial differences in final validation results. The proposed approach ensures geo-tagged photo quality, and supports the sample classification strategy by considering photo distribution, with accuracy improvement from 72.07% to 79.33% compared with solely considering the single nearest photo. Consequently, the presented approach proves the feasibility of deep learning technology on land cover information identification of geo-tagged photos, and has a great potential to support and improve the efficiency of land cover validation. Numéro de notice : A2018-289 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2018.04.025 Date de publication en ligne : 16/05/2018 En ligne : https://doi.org/10.1016/j.isprsjprs.2018.04.025 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90404 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2018071	RAB	Revue	Centre de documentation	En réserve L003	Disponible
081-2018073	DEP-EXM	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2018072	DEP-EAF	Revue	Nancy	Dépôt en unité	Exclu du prêt