Pre-Processing Training Data Improves Accuracy and Generalisability of Convolutional Neural Network Based Landscape Semantic Segmentation

Data pre-processing for developing a generalised land use and land cover (LULC) deep learning model using earth observation data is important for the classification of a different date and/or sensor. However, it is unclear how to approach deep learning segmentation problems in earth observation data...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Andrew Clark, Stuart Phinn, Peter Scarth
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2023-06-01
coleção:	Land
Assuntos:	convolutional neural network deep learning semantic segmentation land use land cover aerial imagery
Acesso em linha:	https://www.mdpi.com/2073-445X/12/7/1268
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!