Comparing OBIA-Generated Labels and Manually Annotated Labels for Semantic Segmentation in Extracting Refugee-Dwelling Footprints

Refugee-dwelling footprints derived from satellite imagery are beneficial for humanitarian operations. Recently, deep learning approaches have attracted much attention in this domain. However, most refugees are hosted by low- and middle-income countries where accurate label data are often unavailabl...

Full description

Bibliographic Details

Published in:	Applied Sciences
Main Authors:	Yunya Gao, Stefan Lang, Dirk Tiede, Getachew Workineh Gella, Lorenz Wendt
Format:	Article
Language:	English
Published:	MDPI AG 2022-11-01
Subjects:	remote sensing deep learning semantic segmentation label noise OBIA refugees
Online Access:	https://www.mdpi.com/2076-3417/12/21/11226