File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TGRS.2021.3049224
- Scopus: eid_2-s2.0-85099724790
- WOS: WOS:000711850900048
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Hyperspectral Anomaly Detection via Deep Plug-and-Play Denoising CNN Regularization
Title | Hyperspectral Anomaly Detection via Deep Plug-and-Play Denoising CNN Regularization |
---|---|
Authors | |
Keywords | Plug-and-play Convolutional neural network (CNN) denoiser Anomaly detection Dictionary construction Hyperspectral image (HSI) |
Issue Date | 2021 |
Citation | IEEE Transactions on Geoscience and Remote Sensing, 2021, v. 59 n. 11, p. 9553-9568 How to Cite? |
Abstract | Due to the importance in many military and civilian applications, hyperspectral anomaly detection has attracted remarkable interest. Low-rank representation (LRR)-based anomaly detectors use the low-rank property to represent background pixels, and pixels that cannot be well represented are detected as anomalies. The ability of an LRR-based detector to separate background pixels and anomalous pixels depends on the dictionary representation ability, which usually can be enhanced by designing a proper prior for dictionary representation coefficients and constructing a better dictionary. However, it is not easy to handcraft effective and meaningful regularizers for dictionary coefficients. In this article, we propose a novel anomaly detection algorithm that uses a plug-and-play prior for representation coefficients and constructs a new dictionary based on clustering. Instead of cumbersomely handcrafting a regularizer for representation coefficients, we propose solving the anomaly detection problem using the plug-and-play framework, which enables us to plug state-of-the-art priors for representation coefficients. An effective convolutional neural network (CNN) denoiser is plugged into our framework to fully exploit the spatial correlation of representation coefficients. We also propose a modified background dictionary construction method, which carefully includes background pixels and excludes anomalous pixels from clustering results. We refer to the proposed anomaly detection method as plug-and-play denoising CNN regularized anomaly detection (DeCNN-AD) method. Extensive experiments were performed on five data sets in a comparison with eight state-of-the-art anomaly detection methods. The experimental results suggest that the proposed method is effective in anomaly detection and can produce better anomaly detection results than that of the comparison methods. The codes of this work will be available at https://github.com/FxyPd for the sake of reproducibility. |
Persistent Identifier | http://hdl.handle.net/10722/298375 |
ISSN | 2023 Impact Factor: 7.5 2023 SCImago Journal Rankings: 2.403 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Fu, Xiyou | - |
dc.contributor.author | Jia, Sen | - |
dc.contributor.author | Zhuang, Lina | - |
dc.contributor.author | Xu, Meng | - |
dc.contributor.author | Zhou, Jun | - |
dc.contributor.author | Li, Qingquan | - |
dc.date.accessioned | 2021-04-08T03:08:17Z | - |
dc.date.available | 2021-04-08T03:08:17Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | IEEE Transactions on Geoscience and Remote Sensing, 2021, v. 59 n. 11, p. 9553-9568 | - |
dc.identifier.issn | 0196-2892 | - |
dc.identifier.uri | http://hdl.handle.net/10722/298375 | - |
dc.description.abstract | Due to the importance in many military and civilian applications, hyperspectral anomaly detection has attracted remarkable interest. Low-rank representation (LRR)-based anomaly detectors use the low-rank property to represent background pixels, and pixels that cannot be well represented are detected as anomalies. The ability of an LRR-based detector to separate background pixels and anomalous pixels depends on the dictionary representation ability, which usually can be enhanced by designing a proper prior for dictionary representation coefficients and constructing a better dictionary. However, it is not easy to handcraft effective and meaningful regularizers for dictionary coefficients. In this article, we propose a novel anomaly detection algorithm that uses a plug-and-play prior for representation coefficients and constructs a new dictionary based on clustering. Instead of cumbersomely handcrafting a regularizer for representation coefficients, we propose solving the anomaly detection problem using the plug-and-play framework, which enables us to plug state-of-the-art priors for representation coefficients. An effective convolutional neural network (CNN) denoiser is plugged into our framework to fully exploit the spatial correlation of representation coefficients. We also propose a modified background dictionary construction method, which carefully includes background pixels and excludes anomalous pixels from clustering results. We refer to the proposed anomaly detection method as plug-and-play denoising CNN regularized anomaly detection (DeCNN-AD) method. Extensive experiments were performed on five data sets in a comparison with eight state-of-the-art anomaly detection methods. The experimental results suggest that the proposed method is effective in anomaly detection and can produce better anomaly detection results than that of the comparison methods. The codes of this work will be available at https://github.com/FxyPd for the sake of reproducibility. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Transactions on Geoscience and Remote Sensing | - |
dc.subject | Plug-and-play | - |
dc.subject | Convolutional neural network (CNN) denoiser | - |
dc.subject | Anomaly detection | - |
dc.subject | Dictionary construction | - |
dc.subject | Hyperspectral image (HSI) | - |
dc.title | Hyperspectral Anomaly Detection via Deep Plug-and-Play Denoising CNN Regularization | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TGRS.2021.3049224 | - |
dc.identifier.scopus | eid_2-s2.0-85099724790 | - |
dc.identifier.volume | 59 | - |
dc.identifier.issue | 11 | - |
dc.identifier.spage | 9553 | - |
dc.identifier.epage | 9568 | - |
dc.identifier.eissn | 1558-0644 | - |
dc.identifier.isi | WOS:000711850900048 | - |
dc.identifier.issnl | 0196-2892 | - |