Consiglio Nazionale delle Ricerche

Tipo di prodottoContributo in atti di convegno
TitoloDependent component analysis as a tool for blind spectral unmixing of remote sensed images
Anno di pubblicazione2006
FormatoElettronico
Autore/iCaiafa C. F., Salerno E., Proto A. N., Fiumi L.
Affiliazioni autoriLaboratorio de Sistemas Complejos. Facultad de Ingeniería. Universidad de Buenos Aires; CNR-ISTI, Pisa, Italy; Comisión de Investigaciones Cientícas de la Prov. de Buenos Aires; CNR-IIA, Roma, Italy
Autori CNR e affiliazioni
  • EMANUELE SALERNO
Lingua/e
  • inglese
AbstractIn this work, we present a blind technique for the estimation of the material abundances per pixel (end-members) in hyperspectral remote-sensed images. Classical spectral unmixing techniques require the knowledge of the existing materials and their spectra. This is a problem when no prior information is available. Some techniques based on independent component analysis proved not to be very efficient for the strong dependence among the material abundances always found in real data. We approach the problem of blind separation of end members by applying the MaxNG algorithm, which is capable to separate even sensibly dependent signals. We also present a minimum-mean-squared-error method to estimate the unknown scale factors by exploiting the source constraint. The results shown here have been obtained from either synthetic or real data. The synthetic images have been generated by a noisy linear mixture model with real, spatially variable, endmember spectra. The real images have been captured by the MIVIS airborne imaging spectrometer. Our results showed that MaxNG is able to separate the endmembers successfully if a linear mixing model holds true and for low noise and reduced spectral variability conditions.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da-
Pagine a-
Pagine totali5
Rivista-
Numero volume della rivista-
Serie/Collana-
Titolo del volume-
Numero volume della serie/collana-
Curatore/i del volume-
ISBN-
DOI-
Editore-
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)-
Parole chiaveRemote Sensing, Spectral Unmixing, Dependent Component Analysis
Link (URL, URI)-
Titolo convegno/congressoEuropean Signal Processing Conference - EUSIPCO 2006
Luogo convegno/congressoFlorence, Italy
Data/e convegno/congresso04-08/09/2006
RilevanzaInternazionale
RelazioneContributo
Titolo parallelo-
Note/Altre informazioniCodice Puma: cnr.isti/2006-A2-38
Strutture CNR
  • ISTI — Istituto di scienza e tecnologie dell'informazione "Alessandro Faedo"
Moduli/Attività/Sottoprogetti CNR
  • ICT.P10.008.006 : Media-Net: Rete di eccellenza CNR e Laboratorio Virtuale per l'analisi e la sintesi di media multidimensionali (mdm)
Progetti Europei-
Allegati
Dependent component analysis as a tool for blind spectral unmixing of remote sensed images (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 disciplinareComputer Science & Engineering
NoteIn: European Signal Processing Conference - EUSIPCO 2006 (Florence, Italy, 4-8 September 2006). Proceedings, pp. -. EURASIP, 2006.
Descrizione sintetica del prodottoABSTRACT: In this work, we present a blind technique for the estimation of the material abundances per pixel (end-members) in hyperspectral remote-sensed images. Classical spectral unmixing techniques require the knowledge of the existing materials and their spectra. This is a problem when no prior information is available. Some techniques based on independent component analysis proved not to be very efficient for the strong dependence among the material abundances always found in real data. We approach the problem of blind separation of end members by applying the MaxNG algorithm, which is capable to separate even sensibly dependent signals. We also present a minimum-mean-squared-error method to estimate the unknown scale factors by exploiting the source constraint. The results shown here have been obtained from either synthetic or real data. The synthetic images have been generated by a noisy linear mixture model with real, spatially variable, endmember spectra. The real images have been captured by the MIVIS airborne imaging spectrometer. Our results showed that MaxNG is able to separate the endmembers successfully if a linear mixing model holds true and for low noise and reduced spectral variability conditions.