Auto-AD: Autonomous Hyperspectral Anomaly Detection Network Based on Fully Convolutional Autoencoder

Hyperspectral anomaly detection is aimed at detecting observations that differ from their surroundings, and is an active area of research in hyperspectral image processing. Recently, autoencoders (AEs) have been applied in hyperspectral anomaly detection; however, the existing AE-based methods are c...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on geoscience and remote sensing Ročník 60; s. 1 - 14
Hlavní autoři:	Wang, Shaoyu, Wang, Xinyu, Zhang, Liangpei, Zhong, Yanfei
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Adaptive-weighted loss Anomalies Anomaly detection autonomous detection Datasets Detection Detectors Errors Estimation Feature extraction fully convolutional autoencoder (AE) hyperspectral anomaly detection Hyperspectral imaging Image processing Image reconstruction Probability theory Training Unmanned aerial vehicles
ISSN:	0196-2892, 1558-0644
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!