Two-Stream Isolation Forest Based on Deep Features for Hyperspectral Anomaly Detection

Hyperspectral anomaly detection (HAD) is a challenging task in hyperspectral image processing, which is to capture the anomaly by spectral and spatial information without prior knowledge. Recently, some isolation forest (IF) methods in the HAD are proposed to achieve good accuracy. However, these me...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE geoscience and remote sensing letters 2023, Vol.20, p.1-5
Hauptverfasser:	Cheng, Xi, Zhang, Min, Lin, Sheng, Zhou, Kexue, Zhao, Shaobo, Wang, Hai
Format:	Artikel
Sprache:	eng
Schlagworte:	Anomalies Anomaly detection Deep features Detection Feature extraction Forestry global and local isolate forest hyperspectral anomaly detection (HAD) Hyperspectral imaging Image processing Information processing Methods Neural networks Principal component analysis Rivers Sensitivity enhancement Spatial data spectral and spatial information Vegetation
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!