当前位置: X-MOL 学术Geocarto Int. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deep Semantic Segmentation for Detecting Eucalyptus Planted Forests in the Brazilian Territory Using Sentinel-2 Imagery
Geocarto International ( IF 3.8 ) Pub Date : 2021-06-14 , DOI: 10.1080/10106049.2021.1943009
Luciana Borges da Costa 1 , Osmar Luiz Ferreira de Carvalho 2 , Anesmar Olino de Albuquerque 1 , Roberto Arnaldo Trancoso Gomes 1 , Renato Fontes Guimarães 1 , Osmar Abílio de Carvalho Júnior 1
Affiliation  

Abstract

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.



中文翻译:

使用 Sentinel-2 图像检测巴西境内桉树人工林的深度语义分割

摘要

本研究旨在分析深度语义分割在使用 Sentinel-2 图像检测桉树造林区域中的应用。该研究比较了六种架构(U-net、DeepLabv3+、FPN、MANet、PSPNet、LinkNet)与四种编码器(ResNet-101、ResNeXt-101、Efficient-net-b3 和 Efficient-net-b7),使用 10 个光谱带. 尽管不同模型之间的差异不大,但我们发现 Efficient-net-b7 是所有架构中最好的主干,最好的整体模型是带有 Efficient-net-b7 主干的 DeepLabv3+,实现了 76.57 的 IoU . 此外,我们将大型卫星图像的映射与考虑六个步幅值的重叠像素的滑动窗口技术进行了比较。我们发现,具有较低步幅值的滑动窗口在视觉和定量(指标)上都显着减少了帧边缘中的错误。语义分割可以区分造林和自然植被,快速有效地分析巴西造林变化的空间分布。

更新日期:2021-06-15
down
wechat
bug