A Residual-Dyad Encoder Discriminator Network for Remote Sensing Image Matching

We propose a new method for remote sensing image matching. The proposed method uses an encoder subnetwork of an autoencoder pretrained on the GTCrossView data to construct image features. A discriminator network trained on the University of California Merced land-use/land-cover data set (LandUse) an...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on geoscience and remote sensing 2020-03, Vol.58 (3), p.2001-2014
Hauptverfasser:	Khurshid, Numan, Tharani, Mohbat, Taj, Murtaza, Qureshi, Faisal Z.
Format:	Artikel
Sprache:	eng
Schlagworte:	Coders Computer architecture Content-based remote sensing image retrieval (CBRSIR) convolutional neural network (CNN) Data Datasets deep learning Engineering Engineering, Electrical & Electronic Feature extraction Geochemistry & Geophysics Image matching Image retrieval Imaging Science & Photographic Technology Land cover Land use Matching Measurement Physical Sciences Remote Sensing residual encoder–decoder RS image search Satellites Science & Technology Task analysis Technology Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!