A dual network for super-resolution and semantic segmentation of sentinel-2 imagery

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 t...

Descripción completa

Detalles Bibliográficos
Autores: Abadal Lloret, Sauc, Salgueiro Romero, Luis Fernando|||0000-0003-4048-8330, Marcello Ruiz, Javier, Vilaplana Besler, Verónica|||0000-0001-6924-9961
Tipo de recurso: artículo
Fecha de publicación:2021
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/360869
Acceso en línea:https://hdl.handle.net/2117/360869
https://dx.doi.org/10.3390/rs13224547
Access Level:acceso abierto
Palabra clave:Remote sensing
Image reconstruction
Deep learning
Super-resolution
Semantic segmentation
Convolutional neural network
Sentinel-2
Teledetecció
Aprenentatge profund
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
Descripción
Sumario: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.