Spatial–Spectral Joint Hyperspectral Anomaly Detection Based on a Two-Branch 3D Convolutional Autoencoder and Spatial Filtering

Hyperspectral anomaly detection (HAD) is an important application of hyperspectral images (HSI) that can distinguish anomalies from background in an unsupervised manner. As a common unsupervised network in deep learning, autoencoders (AE) have been widely used in HAD and can highlight anomalies by r...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Remote sensing (Basel, Switzerland) Jg. 15; H. 10; S. 2542
Hauptverfasser:	Lv, Shuai, Zhao, Siwei, Li, Dandan, Pang, Boyu, Lian, Xiaoying, Liu, Yinnian
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Basel MDPI AG 12.05.2023
Schlagworte:	3D convolutional autoencoder Algorithms Anomalies anomaly detection Artificial intelligence Collaboration Comparative analysis data collection Datasets Decomposition Deep learning hyperspectral image Hyperspectral imaging Image processing Machine learning Methods Morphological filters Multispectral photography Neural networks Normal distribution Remote sensing satellites Sparsity Spatial filtering spatial–spectral joint information Technology application variance China
ISSN:	2072-4292, 2072-4292
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!