Generating Training Data for Deep Learning-Based Segmentation Algorithms by Projecting Existing Labels onto Additional Aerial Images

Highly accurate manually-generated labels in aerial and satellite images are used for the training of deep learning-based segmentation algorithms and should be available in large numbers and cover many different scenarios to increase the accuracy and generalization capability of the underlying model...

ver descrição completa

Detalhes bibliográficos

Principais autores:	F. Kurz, N. Merkle, C. Henry, R. Bahmanyar, F. Rauch, J. Hellekes, V. Gstaiger, D. Rosenbaum, P. Reinartz
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Copernicus Publications 2025-05-01
coleção:	The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Acesso em linha:	https://isprs-archives.copernicus.org/articles/XLVIII-M-6-2025/189/2025/isprs-archives-XLVIII-M-6-2025-189-2025.pdf
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!