Jarry R. auteur aut IRD Chaumont M. auteur aut IRD Berti-Equille Laure auteur aut IRD Subsol G auteur aut IRD text bookSection eng text/pdf born digital access One of the major issues in predicting poverty with satellite images is the lack of fine-grained and reliable poverty indicators. To address this problem, various methodologies were proposed recently. Most recent approaches use a proxy (e.g., nighttime light), as an additional information, to mitigate the problem of sparse data. They consist in building and training a CNN with a large set of images, which is then used as a feature extractor. Ultimately, pairs of extracted feature vectors and poverty labels are used to learn a regression model to predict the poverty indicators.First, we propose a rigorous comparative study of such approaches based on a unified framework and a common set of images. We observed that the geographic displacement on the spatial coordinates of poverty observations degrades the prediction performances of all the methods. Therefore, we present a new methodology combining grid-cell selection and ensembling that improves the poverty prediction to handle coordinate displacement. specialized 126 122 Del Bimbo A. ed. edt IRD Cucchiara R. ed. edt IRD Sclaroff S. ed. edt IRD Farinella G.M. ed. edt IRD Mei T. ed. edt IRD Bertini M. ed. edt IRD Escalante H.J. ed. edt IRD Vezzani R. ed. edt IRD 12667 550-565 Cham Springer 2021 ICPR.International Workshops and Challenges, [En ligne], 2021/01/10-15 12667 https://www.documentation.ird.fr/hor/fdi:010085560 10.1007/978-3-030-68787-8_40 978-3-030-68786-1 [F B010085560] https://www.documentation.ird.fr/hor/fdi:010085560 https://www.documentation.ird.fr/intranet/publi/2023-01/010085560.pdf Accès réservé (Intranet de l'IRD) IRD - Base Horizon / Pleins textes 2022-06-29 2025-02-24 fdi:010085560 fre