Atualização de Documento

XIX SBSR

Formulário de atualização

O sistema de atualização, para eventuais correções, estará ativo até 30/11/2019.

Contato: bibdigital@inpe.br


Nome do Campo		Valor do Campo
Tipo de Referência		Artigo em Evento (Conference Proceedings)
Título do Trabalho	(*)(?)
	Não esqueça de clicar na opção "+" para informar os dados dos co-autores, se tiver.		v
1° Autor	(*)(?)
Grupo (1° Autor)
Afiliação (1° Autor)
e-Mail (1° Autor)
2° Autor	(*)(?)
Grupo (2° Autor)
Afiliação (2° Autor)
e-Mail (2° Autor)
3° Autor	(*)(?)
Grupo (3° Autor)
Afiliação (3° Autor)
e-Mail (3° Autor)
4° Autor	(*)(?)
Grupo (4° Autor)
Afiliação (4° Autor)
e-Mail (4° Autor)
Páginas	(*)
Tipo Secundário
Palavras-Chave	(*)(?)
Resumo	(*)(?)	Biomes like the Amazon Rainforest are a challenge for change detection analysis due to high frequency of clouds. Moreover, time series analysis to change detection in Tropical Rainforests are still recent. This work investigates how a TM/NDVI time series constructed from object-images can help understand the deforestation process in the Amazon Rainforest over 28 years. The study area is located in the state of Mato Grosso, Brazil, within the Arc of Deforestation. We used the bfastSpatial package to obtain the mean annual behaviour of object-based time series from 1984 to 2011. Moreover, we have also detected deforestation in 2002, extracting the lower mean value of each object in this period. To evaluate the proposed method, we compare the processing time between a time series object-based and pixel level. Deforestation initiated in the 90s, with an intensification of the process in the early 2000s. The peak of deforestation observed from this period can be related to an increase in agricultural commodities prices, especially soybeans and meat in the early 2000s. The validation to deforestation detection in 2002 has resulted in a producers accuracy of 85%. Construction of time series by applying an object-based methodology reduced the computational time in 95% and removed the influence of salt-pepper effect. The combination of these factors, may have contributed to the quality this result, representing a new approach for time series analysis.
Tema	(*)
FileName	(?)
e-Mail (login)		banon