Portal de Periódicos da CAPES

Artigo Produção Nacional Revisado por pares

BIBTEX RIS

Deep semantic segmentation for detecting eucalyptus planted forests in the Brazilian territory using sentinel-2 imagery

2021; Taylor & Francis; Volume: 37; Issue: 22 Linguagem: Inglês

10.1080/10106049.2021.1943009

1752-0762

Luciana Borges da Costa, Osmar Luiz Ferreira de Carvalho, Anesmar Olino de Albuquerque, Roberto Arnaldo Trancoso Gomes, Renato Fontes Guimarães, Osmar Abílio de Carvalho Júnior,

Land Use and Ecosystem Services

This research aims to analyze the use of deep semantic segmentation to detect eucalyptus afforestation areas using Sentinel-2 images. The study compared six architectures (U-net, DeepLabv3+, FPN, MANet, PSPNet, LinkNet) with four encoders (ResNet-101, ResNeXt-101, Efficient-net-b3 and Efficient-net-b7), using 10 spectral bands. Even though the differences were not large among the different models, we found that the Efficient-net-b7 was the best backbone among all architectures, and the best overall model was DeepLabv3+ with the Efficient-net-b7 backbone, achieving an IoU of 76.57. Moreover, we compared the mapping of large satellite images with the sliding window technique with overlapping pixels considering six stride values. We found that sliding windows with lower stride values significantly minimized errors in the frame edge both visually and quantitively (metrics). Semantic segmentation allows an evident distinction between the afforestation and the natural vegetation, being fast and efficient for spatial distribution analysis of afforestation changes in Brazil.