| Texto completo | |
| Autor(es): |
de Santiago Junior, Valdivino Alexandre
;
Miranda, Mateus de Souza
;
Rodrigues, Marcos Lima
;
de Castro e Silva, Baggio Luiz
;
Korting, Thales Sehn
Número total de Autores: 5
|
| Tipo de documento: | Artigo Científico |
| Fonte: | REVISTA GEOARAGUAIA; v. 15, n. 1, p. 24-pg., 2025-06-01. |
| Resumo | |
While the semantic segmentation task has long been studied by the remote sensing (RS) community, it is a fact that deep neural networks (DNNs) have drawn attention due to the great interest and success of deep learning in several application domains. Even if there are so many studies and experiments using DNNs for RS semantic segmentation, an in-depth multi-view evaluation considering not only different DNNs but also distinct types of images (optical, multispectral) and satellite sensors with diverse spatial resolutions is still missing. This article presents one of such an experimentation where the following options were considered: (1) images from three different satellites, i.e., Landsat-8 (30 m of spatial resolution), Sentinel-2 (10 m of spatial resolution), China-Brazil Earth Resources-4A (CBERS-4A; 8 m of spatial resolution); (2) three classical DNNs, i.e., U-Net, DeepLabV3+, PSPNet; and (3) two types of images (optical (RGB) and multispectral). The selected study area was the Brazilian Cerrado savanna and the choices of the evaluation focused more on the state-of-the-practice. A thorough investigation was performed and results show that DNNs and spatial resolution of satellite sensors are more relevant than the types of images. This conclusion is interesting because, eventually, researchers may rely on images with less number of channels (optical), decreasing the computational effort during training the DNNs. (AU) | |
| Processo FAPESP: | 23/09118-6 - Descoberta de conteúdo em catálogos de imagens de sensoriamento remoto |
| Beneficiário: | Thales Sehn Körting |
| Modalidade de apoio: | Auxílio à Pesquisa - Regular |