Global Information and Structure Tensor Guided Collaborative Representation for Anomaly Detection
Anomaly detection is susceptible to complex background and interference noise. Local anomaly detection and collaborative representation detection can effectively suppress background. However, they both encounter the problem of window size determination due to unexpectable target size, which will str...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10767194/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592923001094144 |
|---|---|
| author | Meiping Song Zhenyu Guo Lan Li Shihui Liu Haimo Bao Jiakang Li |
| author_facet | Meiping Song Zhenyu Guo Lan Li Shihui Liu Haimo Bao Jiakang Li |
| author_sort | Meiping Song |
| collection | DOAJ |
| description | Anomaly detection is susceptible to complex background and interference noise. Local anomaly detection and collaborative representation detection can effectively suppress background. However, they both encounter the problem of window size determination due to unexpectable target size, which will strongly limit their detection performance. On the other hand, some interferences show similar properties with anomalies, namely small, weak and in low probability, which would be wrongly reputed as anomalies and degrade the detection accuracy too. A global information and structure tensor guided collaborative representation detection method is proposed in this article. First, the global and local information are combined into the collaborative representation to obtain a more valuable background dictionary, preventing the big targets from being missed. Second, to address the problem that anomaly targets are susceptible to interference spectra, an improved structure tensor is introduced into the band selection and detection refining. Bands of better spatial representation for anomaly are selected for detecting, and interference spectra are removed from representation residual to refine the detection result. Experiments on the real datasets show that the method performs better than classical and some recently proposed methods in background and interference suppression, and achieves satisfactory anomaly detection precision. |
| format | Article |
| id | doaj-art-524a02e2ec17477787aa2ed87358d317 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-524a02e2ec17477787aa2ed87358d3172025-01-21T00:00:38ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183236325210.1109/JSTARS.2024.350611610767194Global Information and Structure Tensor Guided Collaborative Representation for Anomaly DetectionMeiping Song0https://orcid.org/0000-0002-4489-5470Zhenyu Guo1https://orcid.org/0009-0000-4978-7914Lan Li2https://orcid.org/0000-0002-3175-4169Shihui Liu3https://orcid.org/0000-0002-6697-7899Haimo Bao4https://orcid.org/0000-0001-5706-2155Jiakang Li5https://orcid.org/0009-0007-6843-0233Center for Hyperspectral Imaging in Remote Sensing, Information Science and Technology College, Dalian Maritime University, Dalian, ChinaCenter for Hyperspectral Imaging in Remote Sensing, Information Science and Technology College, Dalian Maritime University, Dalian, ChinaCenter for Hyperspectral Imaging in Remote Sensing, Information Science and Technology College, Dalian Maritime University, Dalian, ChinaCenter for Hyperspectral Imaging in Remote Sensing, Information Science and Technology College, Dalian Maritime University, Dalian, ChinaSchool of Innovation Design, Guangzhou Academy of Fine Arts, Guangzhou, ChinaZhengzhou Tobacco Research Institute of CNTC, Zhengzhou, ChinaAnomaly detection is susceptible to complex background and interference noise. Local anomaly detection and collaborative representation detection can effectively suppress background. However, they both encounter the problem of window size determination due to unexpectable target size, which will strongly limit their detection performance. On the other hand, some interferences show similar properties with anomalies, namely small, weak and in low probability, which would be wrongly reputed as anomalies and degrade the detection accuracy too. A global information and structure tensor guided collaborative representation detection method is proposed in this article. First, the global and local information are combined into the collaborative representation to obtain a more valuable background dictionary, preventing the big targets from being missed. Second, to address the problem that anomaly targets are susceptible to interference spectra, an improved structure tensor is introduced into the band selection and detection refining. Bands of better spatial representation for anomaly are selected for detecting, and interference spectra are removed from representation residual to refine the detection result. Experiments on the real datasets show that the method performs better than classical and some recently proposed methods in background and interference suppression, and achieves satisfactory anomaly detection precision.https://ieeexplore.ieee.org/document/10767194/Anomaly detectionband selectioncollaborative representation detection |
| spellingShingle | Meiping Song Zhenyu Guo Lan Li Shihui Liu Haimo Bao Jiakang Li Global Information and Structure Tensor Guided Collaborative Representation for Anomaly Detection IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Anomaly detection band selection collaborative representation detection |
| title | Global Information and Structure Tensor Guided Collaborative Representation for Anomaly Detection |
| title_full | Global Information and Structure Tensor Guided Collaborative Representation for Anomaly Detection |
| title_fullStr | Global Information and Structure Tensor Guided Collaborative Representation for Anomaly Detection |
| title_full_unstemmed | Global Information and Structure Tensor Guided Collaborative Representation for Anomaly Detection |
| title_short | Global Information and Structure Tensor Guided Collaborative Representation for Anomaly Detection |
| title_sort | global information and structure tensor guided collaborative representation for anomaly detection |
| topic | Anomaly detection band selection collaborative representation detection |
| url | https://ieeexplore.ieee.org/document/10767194/ |
| work_keys_str_mv | AT meipingsong globalinformationandstructuretensorguidedcollaborativerepresentationforanomalydetection AT zhenyuguo globalinformationandstructuretensorguidedcollaborativerepresentationforanomalydetection AT lanli globalinformationandstructuretensorguidedcollaborativerepresentationforanomalydetection AT shihuiliu globalinformationandstructuretensorguidedcollaborativerepresentationforanomalydetection AT haimobao globalinformationandstructuretensorguidedcollaborativerepresentationforanomalydetection AT jiakangli globalinformationandstructuretensorguidedcollaborativerepresentationforanomalydetection |