Assessment of CNN-based Methods for Poverty Estimation from Satellite Images - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Assessment of CNN-based Methods for Poverty Estimation from Satellite Images

Résumé

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.
Fichier principal
Vignette du fichier
ICPR2020.pdf (2.39 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03066937 , version 1 (15-12-2020)

Identifiants

Citer

Robin Jarry, Marc Chaumont, Laure Berti-Équille, Gérard Subsol. Assessment of CNN-based Methods for Poverty Estimation from Satellite Images. PRRS 2021 - 11th IAPR International Workshop on Pattern Recognition in Remote Sensing, Jan 2021, Milan, Italy. pp.550-565, ⟨10.1007/978-3-030-68787-8_40⟩. ⟨hal-03066937⟩
387 Consultations
368 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More