Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
A comparison of paired histogram, maximum likelihood, class elimination, and neural network approaches for daylight global cloud classification usingAVHRR imagery
Autore:
Berendes, TA; Kuo, KS; Logar, AM; Corwin, EM; Welch, RM; Baum, BA; Pretre, A; Weger, RC;
Indirizzi:
UnivALlabama, Global Hydrol & Climate Ctr, Dept Atmospher Sci, Huntsville,Univ Alabama Huntsville AL USA 35806 Ctr, Dept Atmospher Sci, Huntsville, SADakota Sch Mines & Technol, Dept Math & Comp Sci, Rapid City, SD 57701 US S Dakota Sch Mines & Technol Rapid City SD USA 57701 id City, SD 57701 US NASA, Div Atmospher Sci, Langley Res Ctr, Hampton, VA 23681 USA NASA Hampton VA USA 23681 her Sci, Langley Res Ctr, Hampton, VA 23681 USA Martin & Associates Inc, Mitchell, SD 57301 USA Martin & Associates Inc Mitchell SD USA 57301 Inc, Mitchell, SD 57301 USA S Dakota Sch Mines & Technol, Inst Atmospher Sci, Rapid City, SD 57701 USAS Dakota Sch Mines & Technol Rapid City SD USA 57701 d City, SD 57701 USA
Titolo Testata:
JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES
fascicolo: D6, volume: 104, anno: 1999,
pagine: 6199 - 6213
Fonte:
ISI
Lingua:
ENG
Soggetto:
RADIOMETER INFRARED CHANNELS; SURFACE CLASSIFICATION; SATELLITE MEASUREMENTS; MULTISPECTRAL IMAGERY; PATTERN-RECOGNITION; COVER ANALYSIS; POLAR-REGIONS; RESOLUTION; CALIBRATION;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Physical, Chemical & Earth Sciences
Citazioni:
39
Recensione:
Indirizzi per estratti:
Indirizzo: Berendes, TA UnivALlabama, Global Hydrol & Climate Ctr, Dept Atmospher Sci, Huntsville, Univ Alabama Huntsville AL USA 35806 ospher Sci, Huntsville,
Citazione:
T.A. Berendes et al., "A comparison of paired histogram, maximum likelihood, class elimination, and neural network approaches for daylight global cloud classification usingAVHRR imagery", J GEO RES-A, 104(D6), 1999, pp. 6199-6213

Abstract

The accuracy and efficiency of four approaches to identifying clouds and aerosols in remote sensing imagery are compared. These approaches are as follows: a maximum likelihood classifier, a paired histogram technique, a hybrid class elimination approach, and a backpropagation neural network. Regional comparisons were conducted on advanced very high resolution radiometer (AVHRR) local area coverage (LAC) scenes from the polar regions, desert areas, and regions of biomass-burning, areas which are known to be particularlydifficult. For the polar, desert, and biomass burning regions, the maximumlikelihood classifier achieved 94-97% accuracy, the neural network achieved 95-96% accuracy, and the paired histogram approach achieved 93-94% accuracy. The primary advantage to the class elimination scheme lies in its speed; its accuracy of 94-96% is comparable to that of the maximum likelihood classifier. Experiments also clearly demonstrate the effectiveness of decomposing a single global classifier into separate regional classifiers, since the regional classifiers can be more finely tuned to recognize local conditions. In addition, the effectiveness of using composite features is comparedto the simpler approach of using the five AVHRR channels and the reflectance of channel 3 treated as a sixth channel as the elements of the feature vector. The results varied, demonstrating that the features cannot be chosenindependently of the classifier to be used. It is also shown that superiorresults can obtained by training the classifiers using subclass information and collapsing the subclasses after classification. Finally, ancillary data were incorporated into the classifiers, consisting of a land/water mask,a terrain map, and a computed sunglint probability. While the neural network did not benefit from this information, the accuracy of the maximum likelihood classifier improved by 1%, and the accuracy of the paired histogram method increased by up to 4%.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 09/04/20 alle ore 11:49:50