Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Class-Aware Trusted Urban Land-Cover Training Labels for 46 African Cities

Domaine:

geospatial

Type de record:

dataset
Créateur:
Koj
Éditeur:
Koj
Éditeur:
Har
Hôte:avatar
This dataset accompanies the manuscript A Class-Aware Trusted-Label Generation Framework for Urban Land-Cover Classification Across Diverse African Ecological Settings. It contains the trusted urban land-cover labels generated across 46 African cities, manual validation records, class confidence assignments, and supporting metadata used to evaluate the proposed framework. Sentinel-2 imagery was accessed through Google Earth Engine and is therefore not redistributed. High-resolution Google Satellite imagery used for manual interpretation is subject to third-party licensing and is not included.

Visit

doi.org

Tasks

computer visionimage classification

Tags

Earth and Environmental SciencesRemote Sensing training labels

Licenses

info:eu-repo/semantics/openAccessCreative Commons Zero v1.0 Universalhttps://creativecommons.org/publicdomain/zero/1.0/legalcode