Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Change detection using adaptive fuzzy neural networks: Environmental damage assessment after the Gulf War
Autore:
Abuelgasim, AA; Ross, WD; Gopal, S; Woodcock, CE;
Indirizzi:
Boston Univ, Dept Geog, Boston, MA 02215 USA Boston Univ Boston MA USA 02215 ton Univ, Dept Geog, Boston, MA 02215 USA NASA, Goddard Space Flight Ctr, Greenbelt, MD 20771 USA NASA Greenbelt MDUSA 20771 ard Space Flight Ctr, Greenbelt, MD 20771 USA MIT, Cambridge, MA 02139 USA MIT Cambridge MA USA 02139MIT, Cambridge, MA 02139 USA
Titolo Testata:
REMOTE SENSING OF ENVIRONMENT
fascicolo: 2, volume: 70, anno: 1999,
pagine: 208 - 223
SICI:
0034-4257(199911)70:2<208:CDUAFN>2.0.ZU;2-E
Fonte:
ISI
Lingua:
ENG
Soggetto:
MAXIMUM-LIKELIHOOD CLASSIFICATION; RESOLUTION SATELLITE DATA; REMOTELY-SENSED DATA; MIXED PIXELS; LANDSAT TM; FEATURES; MAPS;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Physical, Chemical & Earth Sciences
Citazioni:
27
Recensione:
Indirizzi per estratti:
Indirizzo: Gopal, S Boston Univ, Dept Geog, 675 Commonwealth Ave, Boston, MA 02215 USA Boston Univ 675 Commonwealth Ave Boston MA USA 02215 MA 02215 USA
Citazione:
A.A. Abuelgasim et al., "Change detection using adaptive fuzzy neural networks: Environmental damage assessment after the Gulf War", REMOT SEN E, 70(2), 1999, pp. 208-223

Abstract

This article introduces an adaptive fuzzy neural network classifier for environmental change detection and classification applied to monitor landcover changes resulting from the Gulf War. In this study, landcover change is treated as a qualitative shift between landcover categories. The Change Detection Adaptive Fuzzy (CDAF) network learns fuzzy membership functions for each landcover class present at the first image date based on a sample of the image data. An image from a later date is then classified using this network to recognize change among familiar classes as well as change to unfamiliar landcover classes. The CDAF network predicts landcover change with 86% accuracy representing an improvement over both a standard multidate K-meanstechnique which performed at 70% accuracy and a hybrid approach using a maximum likelihood classifier (MLC)/K-means which achieved 65% accuracy. In this study, we developed a hybrid classified based on conventional statistical methods (MLC/K-means classifier) for comparison purposes to help evaluate the performance of the CDAF network. The CDAF compared with existing change detection methodology has two features that lead to significant performance improvements: 1) new landcover types created by a change event automatically lead to the establishment of new landcover categories through an unsupervised learning strategy, and 2) for each pixel the distribution of fuzzymembership values across possible categories are compared to determine whether a significant change has occurred. (C)Elsevier Science Inc., 1999.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 20/09/20 alle ore 07:36:49