Hyperspectral Unmixing Based on Constrained Bilinear or Linear-Quadratic Matrix Factorization

Unsupervised hyperspectral unmixing methods aim to extract endmember spectra and infer the proportion of each of these spectra in each observed pixel when considering linear mixtures. However, the interaction between sunlight and the Earth's surface is often very complex, so that observed spect...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Remote sensing (Basel, Switzerland) Switzerland), 2021-06, Vol.13 (11), p.2132, Article 2132
Hauptverfasser:	Benhalouche, Fatima Zohra, Deville, Yannick, Karoui, Moussa Sofiane, Ouamri, Abdelaziz
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms bilinear or linear-quadratic matrix factorization Choice learning Constraints Data models Earth surface endmember spectra extraction Environmental Sciences Environmental Sciences & Ecology Experiments Factorization Geology Geosciences, Multidisciplinary Hyperspectral imaging Imaging Science & Photographic Technology Life Sciences & Biomedicine Machine learning Methods Nonlinear systems Nonlinearity nonnegativity constraints Optimization Performance evaluation Physical Sciences Remote Sensing Science & Technology Sensors Signal processing Spectra Technology unsupervised bilinear or linear-quadratic spectral unmixing
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!