Iterative Spectral Distancing: A Novel Approach for Extracting Endmembers in Complex Urban Image Scenes

Onderzoeksoutput: Conference paper

1 Citaat (Scopus)

Samenvatting

Optical remote sensing images of cities exhibit strong spectral variability, and characterising it remains a key challenge. Imaging spectroscopy is useful for this purpose, yet traditional endmember extraction algorithms are poorly suited for this type of imagery. Important issues include the non-spatiality, randomness and poor computational efficiency of existing methods, as well as the need for predefining the number of endmembers. We propose a novel algorithm, called Iterative Spectral Distancing addressing each of these issues. We show that ISD outperforms three established methods on a synthetic image, indicating its potential.
Originele taal-2English
Titel2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS
UitgeverijIEEE
Pagina's4035-4038
Aantal pagina's4
ISBN van geprinte versie978-166540369-6
DOI's
StatusPublished - 2021
EvenementIGARSS 2021 - Brussels, Belgium
Duur: 12 jul 202116 jul 2021

Conference

ConferenceIGARSS 2021
LandBelgium
StadBrussels
Periode12/07/2116/07/21

Vingerafdruk

Duik in de onderzoeksthema's van 'Iterative Spectral Distancing: A Novel Approach for Extracting Endmembers in Complex Urban Image Scenes'. Samen vormen ze een unieke vingerafdruk.

Citeer dit