Urban surfaces are highly inhomogeneous because of the high spatial and spectral diversity of man-made structures. Spectral unmixing techniques although developed to be used with hyperspectral data, are useful for assessing sub-pixel information on multispectral data as well. The large spectral variability imposes the use of multiple endmember spectral mixture analysis techniques, in which many possible mixture models are considered to produce the best fit. The use of many endmembers and mixture models result in prohibitive computational time. In this study, an artificial neural network is used to inverse the pixel spectral mixture in Landsat imagery. Endmember spectra, collected from the image were used to train the network and capture the spectral variability of man-made structures.

Mitraka, Z., DEL FRATE, F. (2015). Non-linear spectral mixture analysis of Landsat imagery by means of neural networks. In International Geoscience and Remote Sensing Symposium (IGARSS) (pp.1765-1768). Institute of Electrical and Electronics Engineers Inc. [10.1109/IGARSS.2015.7326131].

Non-linear spectral mixture analysis of Landsat imagery by means of neural networks

DEL FRATE, FABIO
2015-01-01

Abstract

Urban surfaces are highly inhomogeneous because of the high spatial and spectral diversity of man-made structures. Spectral unmixing techniques although developed to be used with hyperspectral data, are useful for assessing sub-pixel information on multispectral data as well. The large spectral variability imposes the use of multiple endmember spectral mixture analysis techniques, in which many possible mixture models are considered to produce the best fit. The use of many endmembers and mixture models result in prohibitive computational time. In this study, an artificial neural network is used to inverse the pixel spectral mixture in Landsat imagery. Endmember spectra, collected from the image were used to train the network and capture the spectral variability of man-made structures.
IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015
ita
2015
The Institute of Electrical and Electronics Engineers Geoscience and Remote Sensing Society (IEEE GRSS)
Rilevanza internazionale
contributo
2015
Settore ING-INF/02 - CAMPI ELETTROMAGNETICI
English
Landsat; neural networks; spectral unmixing; urban; earth and planetary sciences (all); computer science applications1707 computer vision and pattern recognition
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7326131&refinements=4291944822&refinements=4226718319&refinements=4226495737&searchWithin=%22First%20Name%22:Fabio&searchWithin=%22Last%20Name%22:Del%20Frate
Intervento a convegno
Mitraka, Z., DEL FRATE, F. (2015). Non-linear spectral mixture analysis of Landsat imagery by means of neural networks. In International Geoscience and Remote Sensing Symposium (IGARSS) (pp.1765-1768). Institute of Electrical and Electronics Engineers Inc. [10.1109/IGARSS.2015.7326131].
Mitraka, Z; DEL FRATE, F
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2108/154007
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 2
social impact