Título:	Dealing with clouds and seasonal changes for center pivot irrigation systems detection using Instance segmentation in sentinel-2 time series
Autor(es):	Albuquerque, Anesmar Olino de Carvalho, Osmar Luiz Ferreira de Silva, Cristiano Rosa e Luiz, Argélica Saiaka Bem, Pablo Pozzobon de Gomes, Roberto Arnaldo Trancoso Guimarães, Renato Fontes Carvalho Júnior, Osmar Abílio de
ORCID:	https://orcid.org/0000-0003-1561-7583 https://orcid.org/0000-0002-5619-8525 https://orcid.org/0000-0003-1189-3337 https://orcid.org/0000-0003-2738-465X https://orcid.org/0000-0003-3868-8704 https://orcid.org/0000-0003-4724-4064 https://orcid.org/0000-0002-9555-043X https://orcid.org/0000-0002-0346-1684
Afiliação do autor:	University of Brasilia, Department of Geography University of Brasilia, Department of Computer Science University of Brasilia, Department of Geography University of Brasilia, Department of Geography University of Brasilia, Department of Geography University of Brasilia, Department of Geography University of Brasilia, Department of Geography University of Brasilia, Department of Geography
Assunto:	Nuvens Aprendizagem profunda Séries temporais
Data de publicação:	13-Ago-2021
Editora:	IEEE
Referência:	ALBUQUERQUE, Anesmar Olino de et al. Dealing with clouds and seasonal changes for center pivot irrigation systems detection using instance segmentation in sentinel-2 time series. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, [S.l.], v. 14, p. 8447-8857, 2021. DOI: 10.1109/JSTARS.2021.3104726. Disponível em: https://ieeexplore.ieee.org/document/9513599. Acesso em: 18 out. 2023.
Abstract:	The automatic detection of Center Pivot Irrigation Systems (CPIS) is fundamental for establishing public policies, especially in countries with a growth perspective in this technology, like Brazil. Previous studies to detect CPIS using deep learning used single-date optical images, containing limitations due to seasonal changes and cloud cover. Therefore, this research aimed to detect CPIS using Sentinel-2 multitemporal images (containing six dates) and instance segmentation, considering seasonal variations and different proportions of cloudy images, generalizing the models to detect CPIS in diverse situations. We used a novel augmentation strategy, in which, for each iteration, six images were randomly selected from the time series (from a total of 11 dates) in random order. We evaluated the Mask-RCNN model with the ResNext-101 backbone considering the COCO metrics on six testing sets with different ratios of cloudless (< 20%) and cloudy images (> 75%), from six cloudless images and zero cloudy images (6:0) up to one cloudless image and five cloudy images (1:5). We found that using six cloudless images provided the best metrics [80% average precision (AP), 93% AP with a 0.5 intersection over union threshold (AP50)]. However, results were similar (74% AP, 88% AP50) even in extreme scenarios with abundant cloud presence (1:5 ratio). Our method provides a more adaptive and automatic way to map CPIS from time series, significantly reducing interference such as cloud cover, atmospheric effects, shadow, missing data, and lack of contrast with the surrounding vegetation.
Unidade Acadêmica:	Instituto de Ciências Humanas (ICH) Departamento de Geografia (ICH GEA) Instituto de Ciências Exatas (IE) Departamento de Ciência da Computação (IE CIC)
Licença:	This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
DOI:	10.1109/JSTARS.2021.3104726
Aparece nas coleções:	Artigos publicados em periódicos e afins

Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.