Buscar

 

RI UFLA (Universidade Federal de Lavras) >
DCF - Departamento de Ciências Florestais >
DCF - Artigos publicados em periódicos >

Por favor, utilize esse identificador para citar este item ou usar como link: http://repositorio.ufla.br/jspui/handle/1/856

Título: Selection of imagery data and classifiers for mapping Brazilian semideciduous Atlantic forests
Autor(es): Carvalho, Luis Marcelo Tavares de
Clevers, Jan G.P.W.
Skidmore, Andrew K.
Jong, Steven M. de
Assunto: Forest classification
Feature sets
Classifiers
Artificial intelligence
Publicador: Elsevier
Data de publicação: 2004
Referência: CARVALHO, L. M. T. et al. Selection of imagery data and classifiers for mapping Brazilian semideciduous Atlantic forests. International Journal of Applied Earth Observation and Geoinformation, Enschede, v. 5, n. 3, p. 173-186, Sept. 2004.
Abstract: This paper presents a case study on the use of features derived from remote sensing data for mapping the highly fragmented semideciduous Atlantic forest in Brazil. Innovative aspects of this research include the evaluation of different feature sets in order to improve land covermapping. The feature sets were defined based on expert knowledge and on data mining techniques to be input to traditional and machine learning algorithms for pattern recognition, viz. maximum likelihood, univariate decision trees, multivariate decision trees, and neural networks. The results showed that the maximum likelihood classification using temporal texture descriptors as extracted with wavelet transforms was most accurate to classify the semideciduous Atlantic forest. In this study, a special accuracy measure was used: the so-called class mapping accuracy. Maximum likelihood performed relatively well, with forest mapping accuracies ranging from 34.5 to 51.3%. In contrast, accuracies for neural networks ranged from 19.0 to 45.2%. Classification confusion occurred mainly with coffee and eucalyptus plantations. Univariate trees provided the most robust results for different feature sets, with accuracies ranging from 39.6 to 46.7%. Temporal information of vegetation indices was more important than image texture, terrain topography and raw spectral information for discriminating semideciduous Atlantic forest.
URI: http://www.sciencedirect.com/science/article/pii/S0303243404000194
http://repositorio.ufla.br/jspui/handle/1/856
Idioma: en
Aparece nas coleções: DCF - Artigos publicados em periódicos

Arquivos neste Item:

Não há arquivos associados para este Item.

Itens protegidos por copyright, com todos os direitos reservados, Salvo indicação em contrário.


Mostrar estatísticas

 


DSpace Software Copyright © 2002-2007 MIT and Hewlett-Packard - Feedback