Identificador persistente para citar o vincular este elemento:
http://hdl.handle.net/10553/113966
Título: | A dual network for super-resolution and semantic segmentation of sentinel-2 imagery | Autores/as: | Abadal, Saüc Salgueiro, Luis Marcello Ruiz, Francisco Javier Vilaplana, Verónica |
Clasificación UNESCO: | 250404 Fotogrametría geodésica 250407 Geodesia por satélites 332401 Satélites artificiales |
Palabras clave: | Convolutional neural network Deep learning Semantic segmentation Sentinel-2 Super-resolution |
Fecha de publicación: | 2021 | Proyectos: | PID2020-117142GB-I00 MCIN/AEI/10.13039/501100011033 |
Publicación seriada: | Remote Sensing | Resumen: | There is a growing interest in the development of automated data processing workflows that provide reliable, high spatial resolution land cover maps. However, high-resolution remote sensing images are not always affordable. Taking into account the free availability of Sentinel-2 satellite data, in this work we propose a deep learning model to generate high-resolution segmentation maps from low-resolution inputs in a multi-task approach. Our proposal is a dual-network model with two branches: the Single Image Super-Resolution branch, that reconstructs a high-resolution version of the input image, and the Semantic Segmentation Super-Resolution branch, that predicts a high-resolution segmentation map with a scaling factor of 2. We performed several experiments to find the best architecture, training and testing on a subset of the S2GLC 2017 dataset. We based our model on the DeepLabV3+ architecture, enhancing the model and achieving an improvement of 5% on IoU and almost 10% on the recall score. Furthermore, our qualitative results demonstrate the effectiveness and usefulness of the proposed approach. | URI: | http://hdl.handle.net/10553/113966 | ISSN: | 2072-4292 | DOI: | 10.3390/rs13224547 | Fuente: | Remote Sensing [ISSN 2072-4292], v. 13(22), 4547, (Noviembre 2021) |
Colección: | Artículos |
Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.