Unsupervised Anomaly Detection in Hyperspectral Imaging: Integrating Tensor Robust Principal Component Analysis With Autoencoding Adversarial Networks
Hyperspectral (HS) image analysis has gained significant attention due to its ability to capture detailed spectral information across hundreds of bands, making it useful for environmental monitoring and mineral exploration applications. However, detecting anomalies in HS images, especially in comple...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10855416/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540564115947520 |
|---|---|
| author | Atsuya Emoto Ryo Matsuoka |
| author_facet | Atsuya Emoto Ryo Matsuoka |
| author_sort | Atsuya Emoto |
| collection | DOAJ |
| description | Hyperspectral (HS) image analysis has gained significant attention due to its ability to capture detailed spectral information across hundreds of bands, making it useful for environmental monitoring and mineral exploration applications. However, detecting anomalies in HS images, especially in complex scenes, remains challenging. This paper proposes a novel approach for robust anomaly detection by integrating tensor robust principal component analysis (TRPCA) with autoencoding adversarial networks (AEAN). Our method utilizes the AEAN model to learn a nonlinear low-dimensional representation of the spectral characteristics of background regions, which is then incorporated into the TRPCA framework. The TRPCA is further enhanced by incorporating prior knowledge of the sparsity of anomalous regions, enabling more accurate separation of background and anomaly components. This integration, achieved through a plug-and-play alternating direction method of multipliers (PnP-ADMM), significantly improves detection accuracy and robustness. Experimental results on benchmark datasets widely used for HS anomaly detection confirm that the proposed method consistently outperforms conventional techniques, achieving superior area-under-the-curve (AUC) scores across diverse and complex scenes. By leveraging both nonlinear modeling of background characteristics and sparsity-based anomaly separation, this research provides a more accurate and robust solution for HS anomaly detection, highlighting its potential for practical applications in remote sensing. |
| format | Article |
| id | doaj-art-d40485731b5d46f6a7ca39e49ec069c7 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-d40485731b5d46f6a7ca39e49ec069c72025-02-05T00:01:10ZengIEEEIEEE Access2169-35362025-01-0113214222143310.1109/ACCESS.2025.353498110855416Unsupervised Anomaly Detection in Hyperspectral Imaging: Integrating Tensor Robust Principal Component Analysis With Autoencoding Adversarial NetworksAtsuya Emoto0Ryo Matsuoka1https://orcid.org/0000-0003-4774-1183Faculty of Environmental Engineering, The University of Kitakyushu, Kitakyushu, Fukuoka, JapanFaculty of Environmental Engineering, The University of Kitakyushu, Kitakyushu, Fukuoka, JapanHyperspectral (HS) image analysis has gained significant attention due to its ability to capture detailed spectral information across hundreds of bands, making it useful for environmental monitoring and mineral exploration applications. However, detecting anomalies in HS images, especially in complex scenes, remains challenging. This paper proposes a novel approach for robust anomaly detection by integrating tensor robust principal component analysis (TRPCA) with autoencoding adversarial networks (AEAN). Our method utilizes the AEAN model to learn a nonlinear low-dimensional representation of the spectral characteristics of background regions, which is then incorporated into the TRPCA framework. The TRPCA is further enhanced by incorporating prior knowledge of the sparsity of anomalous regions, enabling more accurate separation of background and anomaly components. This integration, achieved through a plug-and-play alternating direction method of multipliers (PnP-ADMM), significantly improves detection accuracy and robustness. Experimental results on benchmark datasets widely used for HS anomaly detection confirm that the proposed method consistently outperforms conventional techniques, achieving superior area-under-the-curve (AUC) scores across diverse and complex scenes. By leveraging both nonlinear modeling of background characteristics and sparsity-based anomaly separation, this research provides a more accurate and robust solution for HS anomaly detection, highlighting its potential for practical applications in remote sensing.https://ieeexplore.ieee.org/document/10855416/Hyperspectral imageanomaly detectiontensor robust principal component analysisautoencoding adversarial networksplug-and-play ADMM |
| spellingShingle | Atsuya Emoto Ryo Matsuoka Unsupervised Anomaly Detection in Hyperspectral Imaging: Integrating Tensor Robust Principal Component Analysis With Autoencoding Adversarial Networks IEEE Access Hyperspectral image anomaly detection tensor robust principal component analysis autoencoding adversarial networks plug-and-play ADMM |
| title | Unsupervised Anomaly Detection in Hyperspectral Imaging: Integrating Tensor Robust Principal Component Analysis With Autoencoding Adversarial Networks |
| title_full | Unsupervised Anomaly Detection in Hyperspectral Imaging: Integrating Tensor Robust Principal Component Analysis With Autoencoding Adversarial Networks |
| title_fullStr | Unsupervised Anomaly Detection in Hyperspectral Imaging: Integrating Tensor Robust Principal Component Analysis With Autoencoding Adversarial Networks |
| title_full_unstemmed | Unsupervised Anomaly Detection in Hyperspectral Imaging: Integrating Tensor Robust Principal Component Analysis With Autoencoding Adversarial Networks |
| title_short | Unsupervised Anomaly Detection in Hyperspectral Imaging: Integrating Tensor Robust Principal Component Analysis With Autoencoding Adversarial Networks |
| title_sort | unsupervised anomaly detection in hyperspectral imaging integrating tensor robust principal component analysis with autoencoding adversarial networks |
| topic | Hyperspectral image anomaly detection tensor robust principal component analysis autoencoding adversarial networks plug-and-play ADMM |
| url | https://ieeexplore.ieee.org/document/10855416/ |
| work_keys_str_mv | AT atsuyaemoto unsupervisedanomalydetectioninhyperspectralimagingintegratingtensorrobustprincipalcomponentanalysiswithautoencodingadversarialnetworks AT ryomatsuoka unsupervisedanomalydetectioninhyperspectralimagingintegratingtensorrobustprincipalcomponentanalysiswithautoencodingadversarialnetworks |