Centre de documentation
scientifique

Water level prediction from social media images with a multi-task ranking approach / P. Chaudhary in ISPRS Journal of photogrammetry and remote sensing, vol 167 (September 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 167 (September 2020) . - pp 252 - 262 Titre : Water level prediction from social media images with a multi-task ranking approach Type de document : Article/Communication Auteurs : P. Chaudhary, Auteur ; Stefano D'Aronco, Auteur ; João P. Leitão, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 252 - 262 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] inondation [Termes IGN] niveau hydrostatique [Termes IGN] régression [Termes IGN] réseau social [Termes IGN] surveillance hydrologique [Termes IGN] vision par ordinateur Résumé : (auteur) Floods are among the most frequent and catastrophic natural disasters and affect millions of people worldwide. It is important to create accurate flood maps to plan (offline) and conduct (real-time) flood mitigation and flood rescue operations. Arguably, images collected from social media can provide useful information for that task, which would otherwise be unavailable. We introduce a computer vision system that estimates water depth from social media images taken during flooding events, in order to build flood maps in (near) real-time. We propose a multi-task (deep) learning approach, where a model is trained using both a regression and a pairwise ranking loss. Our approach is motivated by the observation that a main bottleneck for image-based flood level estimation is training data: it is difficult and requires a lot of effort to annotate uncontrolled images with the correct water depth. We demonstrate how to efficiently learn a predictor from a small set of annotated water levels and a larger set of weaker annotations that only indicate in which of two images the water level is higher, and are much easier to obtain. Moreover, we provide a new dataset, named DeepFlood, with 8145 annotated ground-level images, and show that the proposed multi-task approach can predict the water level from a single, crowd-sourced image with 11 cm root mean square error. Numéro de notice : A2020-549 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.07.003 Date de publication en ligne : 29/07/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.07.003 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95776 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020091	RAB	Revue	Centre de documentation	En réserve L003	Disponible
081-2020093	DEP-RECP	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2020092	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt