Utilize este identificador para referenciar este registo: http://hdl.handle.net/10400.13/1479
Título: Assessing the effectiveness of RapidEye multispectral imagery for vegetation mapping in Madeira Island (Portugal)
Autor: Massetti, Andrea
Sequeira, Miguel Pinto da Silva Menezes de
Pupo, Aida Maria Correia de Nóbrega
Figueiredo, Albano
Guiomar, Nuno
Gil, Artur
Palavras-chave: Land cover mapping
Biodiversity assessment
Land use assessment
Oceanic island
Madeira (Portugal)
.
Faculdade de Ciências da Vida
Data: 2016
Editora: Italian Society of Remote Sensing
Citação: Massetti, A., Sequeira, M.M., Pupo, A., Figueiredo, A., Guiomar, N., & Gil, A. (2016) Assessing the effectiveness of RapidEye multispectral imagery for vegetation mapping in Madeira Island (Portugal). European Journal of Remote Sensing, 49, 643-672.
Resumo: Madeira Island is a biodiversity hotspot due to its high number of endemic/native plant species. In this work we developed and assessed a methodological framework to produce a RapidEye-based vegetation map. Reasonable accuracies were achieved for a 26 categories classification scheme in two different seasons. We tested pixel and object based approaches and the inclusion of a vegetation index band on top of the pre-processed RapidEye bands stack. Object based generally showed to outperform pixel based classification approaches except for linear or highly scattered classes. The addition of a vegetation index to the workflow increased the separability of the Jeffrey-Matusita least separable class pairs, but not necessarily the overall accuracy. The Pontius accuracy assessment highlighted class specific accuracy tradeoffs related to different combinations of the inputs and methods. The approach to be used, in conclusion, should be carefully considered on the basis of the desired result.
URI: http://hdl.handle.net/10400.13/1479
DOI: http://dx.doi.org/10.5721/EuJRS20164934
ISSN: 2279-7254
Aparece nas colecções:Artigos em revistas internacionais

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
Sequeira.pdf2,41 MBAdobe PDFVer/Abrir


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote Degois 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.