Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
AN ITERATIVE CLASSIFICATION APPROACH FOR MAPPING NATURAL-RESOURCES FROM SATELLITE IMAGERY
Autore:
SANMIGUELAYANZ J; BIGING GS;
Indirizzi:
COMMISS EUROPEAN COMMUNITIES,JOINT RES CTR,INST REMOTE SENSING APPLICAT,ADV TECH UNIT I-21020 ISPRA VA ITALY EUROPEAN SPACE AGCY,EUROPEAN SPACE RES & TECHNOL CTR,SIGNAL & IMAGE PROC SECT WDP 2200 AG NOORDWIJK NETHERLANDS UNIV CALIF BERKELEY,DEPT ENVIRONM SCI POLICY & MANAGEMENT BERKELEY CA94720
Titolo Testata:
International journal of remote sensing
fascicolo: 5, volume: 17, anno: 1996,
pagine: 957 - 981
SICI:
0143-1161(1996)17:5<957:AICAFM>2.0.ZU;2-Y
Fonte:
ISI
Lingua:
ENG
Soggetto:
MAXIMUM-LIKELIHOOD CLASSIFICATION; REMOTELY SENSED DATA; SPOT HRV IMAGERY; ACCURACY ASSESSMENT; MAP ACCURACY; INTEGRATION; TEXTURE; LANDSAT; GIS;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Science Citation Index Expanded
Science Citation Index Expanded
Citazioni:
47
Recensione:
Indirizzi per estratti:
Citazione:
J. Sanmiguelayanz e G.S. Biging, "AN ITERATIVE CLASSIFICATION APPROACH FOR MAPPING NATURAL-RESOURCES FROM SATELLITE IMAGERY", International journal of remote sensing, 17(5), 1996, pp. 957-981

Abstract

This project explores an iterative classification process as an alternative to two-stage classifications. In the iterative classification approach cover types are classified, one or two at a time, and the bandselection process is repeated in each iteration, so that the combination of bands that provides the best separability among the classes that remain to be classified is selected. The optimum number of bands to perform the classification is also determined for each iteration, so that the classification of the area that is masked in each iteration achieves the highest possible accuracy. Spectral Pattern Analysis, and Spectral Separability Indices are used in the band selection process. GIS analysis is used to obtain prior probabilities, and to determine ifvariables such as elevation, slope, and aspect can result in a sourceof information for segmentation of the study area into more homogeneous strata. The results of this study show that: (1) The proposed iterative classification approach is superior to traditional single-step supervised and unsupervised approaches with a 99 per cent confidence level, and (2) Prior probabilities improve band selection process only when the TD separability index is used, but do not improve the classification process itself. GIS analysis of the study area may serve as a very useful tool for segmenting the study area into more homogeneous strata, but due to the large size of the study area, and the large numberof classes (21 classes) being discriminated it did not help in the classification performed in this study.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 14/08/20 alle ore 07:43:40