Dynamic Low-Rank and Sparse Priors Constrained Deep Autoencoders for Hyperspectral Anomaly Detection

Linear-based low-rank and sparse models (LRSM) and nonlinear-based deep autoencoder (DAE) models have been proven to be effective for the task of anomaly detection (AD) in hyperspectral images (HSIs). The linear-based LRSM is self-explainable, while it may not characterize the complex scenes well. I...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on instrumentation and measurement Ročník 73; s. 1 - 18
Hlavní autoři: Lin, Sheng, Zhang, Min, Cheng, Xi, Shi, Lei, Gamba, Paolo, Wang, Hai
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Anomalies
Anomaly detection (AD)
Decomposition
deep autoencoder (DAE)
Detectors
Dictionaries
Feature extraction
Hyperspectral imaging
Image reconstruction
joint optimization
low-rank prior
Optimization
Reconstruction
sparse prior
Training
ISSN:0018-9456, 1557-9662
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Linear-based low-rank and sparse models (LRSM) and nonlinear-based deep autoencoder (DAE) models have been proven to be effective for the task of anomaly detection (AD) in hyperspectral images (HSIs). The linear-based LRSM is self-explainable, while it may not characterize the complex scenes well. In contrast, the nonlinear-based DAE is able to extract the discriminative features between the background and anomaly for the complex scenes, whereas it is not self-explainable. To effectively combine the advantages of both, a dynamic low-rank and sparse priors-constrained DAEs (DLRSPs-DAEs) for hyperspectral AD (HAD), in this article, is proposed. In order to utilize the low-rank prior existing in an HSI, a low-rank prior-based DAE (DAE_LR) is designed to generate an excellent background reconstruction effect and terrible anomaly reconstruction performance. Further, to consider the sparsity reflecting the anomalies in the HSI, a DAE that is constrained by the sparse prior obtained by the decomposition of the HSI (DAE_S) is developed. Notably, to make the model more compact, the DAE_LR and DAE_S share a common encoder. To achieve global optimal performance, an end-to-end joint optimization strategy with the consideration of the interaction between the learning of the DAEs and the decomposition of the HSI is proposed. Additionally, to yield better detection performance, a nonlinear fusion strategy is exploited to comprehensively combine the detection results obtained from both the DAE_LR and DAE_S. Extensive experiments conducted on several datasets show that the proposed DLRSPs-DAEs detector achieves tremendous performance with respect to the classical and state-of-the-art detectors.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9456
1557-9662
DOI:10.1109/TIM.2023.3323997