Multiscale Memory Autoencoder and Spatial Filtering for Hyperspectral Anomaly Detection

The hyperspectral anomaly detection (HAD) aims to identify potential anomalies from complex backgrounds. Most reconstruction-based autoencoders equally treat background pixels and anomalies or ignore potential spatial information. In this letter, we propose an HAD method based on multiscale memory a...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE geoscience and remote sensing letters Ročník 22; s. 1 - 5
Hlavní autori: Ma, Ziyang, Zhang, Yongshan, Lian, Yuyun, Jiang, Xinwei, Liu, Xiaobo, Cai, Zhihua
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Piscataway IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Anomalies
Anomaly detection
Autoencoder
Autoencoders
Decoding
Feature extraction
Filtering
hyperspectral anomaly detection (HAD)
Image reconstruction
Information processing
memory module
Memory modules
Pixels
Reconstruction
Spatial data
Spatial filtering
Spatial memory
Spectral analysis
Statistical analysis
Training
ISSN:1545-598X, 1558-0571
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The hyperspectral anomaly detection (HAD) aims to identify potential anomalies from complex backgrounds. Most reconstruction-based autoencoders equally treat background pixels and anomalies or ignore potential spatial information. In this letter, we propose an HAD method based on multiscale memory autoencoder and spatial filtering, abbreviated as SFM2AE. Specifically, by introducing memory modules into different hidden layers of the autoencoder, multiscale reconstruction of background and anomaly pixels is achieved in the spectral domain. In addition, morphological filtering in the spatial domain is used to extract spatial structural information from anomalies. Joint spatial-spectral anomaly detection is achieved by combining multiscale memory autoencoder and spatial filtering. Experiments demonstrate superior detection performance of the proposed method over the state-of-the-art methods.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2025.3528498