Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloComparison of polarimetric SAR observables in terms of classification performance
Anno di pubblicazione2008
FormatoElettronico
Autore/iV. Alberga; G. Satalino; D. K. Staykova
Affiliazioni autoriRMA-Belgium,CNR-ISSIA-Italy,GU-Sweden
Autori CNR e affiliazioni
  • GIUSEPPE SATALINO
Lingua/e
  • inglese
AbstractThe advent of fully polarimetric systems has led to an increased amount of information acquired by synthetic aperture radar (SAR) sensors but also to an increased complexity of the data to be analyzed and interpreted. In particular, the choice of several representations of the data, in terms of different parameters with peculiar characteristics and physical meaning, has been offered. With this work, we intend to address their systematic investigation with a twofold goal: 1) to provide a brief review of the polarimetric representations under consideration, 2) to characterize and compare them with respect to their usefulness for classification purposes. The analysis procedure consists of the accuracy estimation of classification tests performed on different parameters derived from L-band polarimetric SAR data. In order to assure a common basis for their comparison, a neural network classifier, the Multi-Layer Perceptron trained by the Back-Propagation learning rule, was used which permits to operate on the data without making any \emph{a priori} assumption on their statistics. In this way, the considered polarimetric parameters, in general characterized by different statistical distributions, may undergo the same classification process and the results compared. Our results indicate that the overall classification performance varies depending on the polarimetric parameters used. However, these variations are relatively limited and do not permit, at this stage, to define an ``absolute'' best representation to identify the classes under investigation in an optimal way.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da4129
Pagine a4150
Pagine totali22
RivistaInternational journal of remote sensing (Print)
Attiva dal 1980
Editore: Taylor & Francis Ltd.. - London
Paese di pubblicazione: Regno Unito
Lingua: inglese
ISSN: 0143-1161
Titolo chiave: International journal of remote sensing (Print)
Titolo abbreviato: Int. j. remote sens. (Print)
Numero volume della rivista29
Fascicolo della rivista14
DOI10.1080/01431160701840182
Verificato da refereeSì: Internazionale
Stato della pubblicazione-
Indicizzazione (in banche dati controllate)
  • ISI Web of Science (WOS) (Codice:WOS:000257034800009)
Parole chiaveSAR polarimetry, classification, neural networks
Link (URL, URI)http://www.tandfonline.com/doi/abs/10.1080/01431160701840182
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione-
Note/Altre informazioni-
Strutture CNR
  • ISSIA — Istituto di studi sui sistemi intelligenti per l'automazione
Moduli/Attività/Sottoprogetti CNR
  • TA.P06.007.002 : Sistemi e modelli per l'estrazione dell'informazione da segnali ed immagini
Progetti Europei-
Allegati
IJRS2009_pol_classif (documento privato )
Tipo documento: application/pdf

Dati storici
I dati storici non sono modificabili, sono stati ereditati da altri sistemi (es. Gestione Istituti, PUMA, ...) e hanno solo valore storico.
Area disciplinareEarth Sciences
Area valutazione CIVRScienze fisiche
Rivista ISIINTERNATIONAL JOURNAL OF REMOTE SENSING [04770J0]
NoteIn press, accepted 01st June 2007