Kansikuva

Hyperspectral Image Unmixing Incorporating Adjacency Information

While the spectral information contained in hyperspectral images is rich, the spatial resolution of such images is in many cases very low. Many pixel spectra are mixtures of pure materials' spectra and therefore need to be decomposed into their constituents. This work investigates new decomposi...

Täydet tiedot

Tallennettuna:
Bibliografiset tiedot
Päätekijä: Bauer, Sebastian (auth)
Aineistotyyppi: Elektroninen Kirjan osa
Kieli:englanti
Julkaistu: KIT Scientific Publishing 2018
Sarja:Forschungsberichte aus der Industriellen Informationstechnik / Institut für Industrielle Informationstechnik (IIIT), Karlsruher Institut für Technologie
Aiheet:
Technology: general issues
Spektrale Entmischung
spectral unmixing
Blinde Quellentrennung
Hyperspectral image processing
Nichtnegative Matrixzerlegung
nonnegative matrix factorization
blind source separation
Hyperspektrale Bildverarbeitung
Linkit:DOAB: download the publication
DOAB: description of the publication
Tagit: Lisää tagi
Ei tageja, Lisää ensimmäinen tagi!
Kuvaus
Yhteenveto:While the spectral information contained in hyperspectral images is rich, the spatial resolution of such images is in many cases very low. Many pixel spectra are mixtures of pure materials' spectra and therefore need to be decomposed into their constituents. This work investigates new decomposition methods taking into account spectral, spatial and global 3D adjacency information. This allows for faster and more accurate decomposition results.
Ulkoasu:1 electronic resource (XIII, 203 p. p.)
ISBN:KSP/1000081665
9783731507888
Pääsy:Open Access

Samankaltaisia teoksia