Hyperspectral Anomaly Detection via Optimal Kernel and High-Order Moment Correlation Representation
Hyperspectral anomaly detection has been a hot topic in the field of remote sensing due to its potential application prospects. However, anomaly detection still has two typical problems to be solved. First, the target in the hyperspectral image is usually mixed with the background. Thus, the backgro...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9774948/ |
| _version_ | 1818237943921246208 |
|---|---|
| author | Zhuang Li Ye Zhang Junping Zhang |
| author_facet | Zhuang Li Ye Zhang Junping Zhang |
| author_sort | Zhuang Li |
| collection | DOAJ |
| description | Hyperspectral anomaly detection has been a hot topic in the field of remote sensing due to its potential application prospects. However, anomaly detection still has two typical problems to be solved. First, the target in the hyperspectral image is usually mixed with the background. Thus, the background is often misjudged as a target without an effective background suppression strategy resulting in false alarms. Second, the non-Gaussian distribution of the complex background affects the judgment of the detector on the abnormality of the target and leads to missed detection. This article proposes an anomaly detection method based on the optimal kernel and high-order moment correlation representation. In selecting the kernel function, the advantage of the Gaussian kernel in anomaly detection is demonstrated through the analysis of the signal uncertainty principle. On this basis, the optimal kernel is determined with sufficient background suppression by isolation forest. In addition, to reduce the influence of non-Gaussian distribution data on detection, the proposed method adopts high-order moments for statistical correlation representation, which further enhances the separability of the background and target after kernel mapping. The experimental results show that the proposed method can effectively suppress the background. Furthermore, it is confirmed that the Gaussian kernel function is effective in improving anomaly detection accuracy. Moreover, the high-order moment correlation representation can highlight the target after kernel mapping, thereby reducing the false alarm rate and obtaining a better detection result. |
| first_indexed | 2024-12-12T12:33:48Z |
| format | Article |
| id | doaj.art-0cda47e212764c6491ce13ea16f24518 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-12T12:33:48Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-0cda47e212764c6491ce13ea16f245182022-12-22T00:24:23ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01153925393710.1109/JSTARS.2022.31741589774948Hyperspectral Anomaly Detection via Optimal Kernel and High-Order Moment Correlation RepresentationZhuang Li0https://orcid.org/0000-0001-9740-1588Ye Zhang1https://orcid.org/0000-0001-8721-4535Junping Zhang2https://orcid.org/0000-0002-1082-114XDepartment of Information Engineering, School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, ChinaDepartment of Information Engineering, School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, ChinaDepartment of Information Engineering, School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, ChinaHyperspectral anomaly detection has been a hot topic in the field of remote sensing due to its potential application prospects. However, anomaly detection still has two typical problems to be solved. First, the target in the hyperspectral image is usually mixed with the background. Thus, the background is often misjudged as a target without an effective background suppression strategy resulting in false alarms. Second, the non-Gaussian distribution of the complex background affects the judgment of the detector on the abnormality of the target and leads to missed detection. This article proposes an anomaly detection method based on the optimal kernel and high-order moment correlation representation. In selecting the kernel function, the advantage of the Gaussian kernel in anomaly detection is demonstrated through the analysis of the signal uncertainty principle. On this basis, the optimal kernel is determined with sufficient background suppression by isolation forest. In addition, to reduce the influence of non-Gaussian distribution data on detection, the proposed method adopts high-order moments for statistical correlation representation, which further enhances the separability of the background and target after kernel mapping. The experimental results show that the proposed method can effectively suppress the background. Furthermore, it is confirmed that the Gaussian kernel function is effective in improving anomaly detection accuracy. Moreover, the high-order moment correlation representation can highlight the target after kernel mapping, thereby reducing the false alarm rate and obtaining a better detection result.https://ieeexplore.ieee.org/document/9774948/Anomaly detectionGaussian kernel functionhigh-order moment correlation representationhyperspectral imageisolation forestsignal uncertainty principle |
| spellingShingle | Zhuang Li Ye Zhang Junping Zhang Hyperspectral Anomaly Detection via Optimal Kernel and High-Order Moment Correlation Representation IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Anomaly detection Gaussian kernel function high-order moment correlation representation hyperspectral image isolation forest signal uncertainty principle |
| title | Hyperspectral Anomaly Detection via Optimal Kernel and High-Order Moment Correlation Representation |
| title_full | Hyperspectral Anomaly Detection via Optimal Kernel and High-Order Moment Correlation Representation |
| title_fullStr | Hyperspectral Anomaly Detection via Optimal Kernel and High-Order Moment Correlation Representation |
| title_full_unstemmed | Hyperspectral Anomaly Detection via Optimal Kernel and High-Order Moment Correlation Representation |
| title_short | Hyperspectral Anomaly Detection via Optimal Kernel and High-Order Moment Correlation Representation |
| title_sort | hyperspectral anomaly detection via optimal kernel and high order moment correlation representation |
| topic | Anomaly detection Gaussian kernel function high-order moment correlation representation hyperspectral image isolation forest signal uncertainty principle |
| url | https://ieeexplore.ieee.org/document/9774948/ |
| work_keys_str_mv | AT zhuangli hyperspectralanomalydetectionviaoptimalkernelandhighordermomentcorrelationrepresentation AT yezhang hyperspectralanomalydetectionviaoptimalkernelandhighordermomentcorrelationrepresentation AT junpingzhang hyperspectralanomalydetectionviaoptimalkernelandhighordermomentcorrelationrepresentation |