Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
The automated extraction of environmentally relevant features from digitalimagery using Bayesian multi-resolution analysis
Autore:
Pal, C; Swayne, D; Frey, B;
Indirizzi:
Univ Waterloo, Dept Comp Sci, Waterloo, ON N2L 3G1, Canada Univ Waterloo Waterloo ON Canada N2L 3G1 ci, Waterloo, ON N2L 3G1, Canada Univ Guelph, Comp Res Lab Environm, Guelph, ON N1G 2W1, Canada Univ Guelph Guelph ON Canada N1G 2W1 Environm, Guelph, ON N1G 2W1, Canada
Titolo Testata:
ADVANCES IN ENVIRONMENTAL RESEARCH
fascicolo: 4, volume: 5, anno: 2001,
pagine: 435 - 444
SICI:
1093-0191(200111)5:4<435:TAEOER>2.0.ZU;2-0
Fonte:
ISI
Lingua:
ENG
Keywords:
image feature extraction; image analysis; image segmentation; knowledge integration; Bayesian networks; computer vision; ecosystem analysis; monitoring urban growth; hydrologic modeling;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
16
Recensione:
Indirizzi per estratti:
Indirizzo: Pal, C Univ Waterloo, Dept Comp Sci, Waterloo, ON N2L 3G1, Canada Univ Waterloo Waterloo ON Canada N2L 3G1 erloo, ON N2L 3G1, Canada
Citazione:
C. Pal et al., "The automated extraction of environmentally relevant features from digitalimagery using Bayesian multi-resolution analysis", ADV ENV RES, 5(4), 2001, pp. 435-444

Abstract

In this paper, we discuss the use of hierarchical tree-structured Bayesiannetworks for integrating knowledge concerning contextual relationships between environmentally relevant features extracted from digital imagery at multiple resolution scales. In our model, conditional probability distributions over continuous valued observations are parameterized using a mixture ofmultivariate Gaussian distributions. Separate classifiers for pixels and groups of pixels are used as sub-components of the overall model. The Bayesian formalism allows models to be composed in a systematic and statisticallysound manner. We illustrate how this approach can be used to resolve ambiguity leading to classification errors and thus improve techniques for the classification of land use from aerial imagery. We present an example relevant to ecosystem analysis, the monitoring of urban growth and the automatic generation of input parameters for hydrologic models. (C) 2001 Elsevier Science Ltd. All rights reserved.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 31/03/20 alle ore 16:15:32