Feature-Driven Active Learning for Hyperspectral Image Classification

Active learning (AL) has obtained a great success in supervised remotely sensed hyperspectral image classification, since it is able to select highly informative training samples. As an intrinsically biased sampling approach, AL generally favors the selection of samples following discriminative dist...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on geoscience and remote sensing 2018-01, Vol.56 (1), p.341-354
Hauptverfasser:	Liu, Chenying, He, Lin, Li, Zhetao, Li, Jun
Format:	Artikel
Sprache:	eng
Schlagworte:	Active learning Active learning (AL) Classification Data Data transfer (computers) Error analysis Error probability Feature extraction Gabor filtering hyperspectral image classification Hyperspectral imaging Image classification Indexes morphological profiles (MPs) overall error probability Probability theory Profiles Remote sensing Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!