Dim and Small Target Detection Based on Local Feature Prior and Tensor Train Nuclear Norm
When faced with complex scenes containing strong edge contours and noise, there are still more background residuals in the detection results of traditional algorithms, leading to a high false alarm rate. To solve the above problems, we propose an infrared dim and small target detection method that c...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Photonics Journal |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10410248/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850081688016650240 |
|---|---|
| author | Anqing Wu Xiangsuo Fan Lei Min Wenlin Qin Ling Yu |
| author_facet | Anqing Wu Xiangsuo Fan Lei Min Wenlin Qin Ling Yu |
| author_sort | Anqing Wu |
| collection | DOAJ |
| description | When faced with complex scenes containing strong edge contours and noise, there are still more background residuals in the detection results of traditional algorithms, leading to a high false alarm rate. To solve the above problems, we propose an infrared dim and small target detection method that combines local feature prior and tensor train nuclear norm (TTNN). To suppress the strong edge contours, we first establish a background edge contour suppression function based on the structure tensor. Secondly, we propose a multi-frame density peak search algorithm to obtain local feature information by combining the features associated with multiple contiguous frames of the target. Then we use the local feature information and reweighting strategy to constrain the sparse components of the target signal, and describe the background low-rank components by the tensor train nuclear norm. Finally, we separate the target image from the background image using the alternating direction multiplier method. As compared with eight advanced algorithms, the method in this paper has a better background strong edge contour and a stronger noise suppression. |
| format | Article |
| id | doaj-art-b6e6ce1ae87a4f9b8426356220f6d66f |
| institution | DOAJ |
| issn | 1943-0655 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Photonics Journal |
| spelling | doaj-art-b6e6ce1ae87a4f9b8426356220f6d66f2025-08-20T02:44:40ZengIEEEIEEE Photonics Journal1943-06552024-01-0116211410.1109/JPHOT.2024.335118910410248Dim and Small Target Detection Based on Local Feature Prior and Tensor Train Nuclear NormAnqing Wu0https://orcid.org/0000-0001-9399-2771Xiangsuo Fan1https://orcid.org/0000-0002-1685-4989Lei Min2https://orcid.org/0000-0002-3459-6063Wenlin Qin3https://orcid.org/0000-0003-0410-4184Ling Yu4https://orcid.org/0009-0002-8804-8545School of Automation, Guangxi University of Science and Technology, Liuzhou, ChinaSchool of Automation, Guangxi University of Science and Technology, Liuzhou, ChinaInstitute of Optics and Electronics Chinese Academy of Sciences, Chengdu, ChinaSchool of Automation, Guangxi University of Science and Technology, Liuzhou, ChinaSchool of Automation, Guangxi University of Science and Technology, Liuzhou, ChinaWhen faced with complex scenes containing strong edge contours and noise, there are still more background residuals in the detection results of traditional algorithms, leading to a high false alarm rate. To solve the above problems, we propose an infrared dim and small target detection method that combines local feature prior and tensor train nuclear norm (TTNN). To suppress the strong edge contours, we first establish a background edge contour suppression function based on the structure tensor. Secondly, we propose a multi-frame density peak search algorithm to obtain local feature information by combining the features associated with multiple contiguous frames of the target. Then we use the local feature information and reweighting strategy to constrain the sparse components of the target signal, and describe the background low-rank components by the tensor train nuclear norm. Finally, we separate the target image from the background image using the alternating direction multiplier method. As compared with eight advanced algorithms, the method in this paper has a better background strong edge contour and a stronger noise suppression.https://ieeexplore.ieee.org/document/10410248/Infrared target detectionstrong edge contours and strong noisetensor train nuclear norm |
| spellingShingle | Anqing Wu Xiangsuo Fan Lei Min Wenlin Qin Ling Yu Dim and Small Target Detection Based on Local Feature Prior and Tensor Train Nuclear Norm IEEE Photonics Journal Infrared target detection strong edge contours and strong noise tensor train nuclear norm |
| title | Dim and Small Target Detection Based on Local Feature Prior and Tensor Train Nuclear Norm |
| title_full | Dim and Small Target Detection Based on Local Feature Prior and Tensor Train Nuclear Norm |
| title_fullStr | Dim and Small Target Detection Based on Local Feature Prior and Tensor Train Nuclear Norm |
| title_full_unstemmed | Dim and Small Target Detection Based on Local Feature Prior and Tensor Train Nuclear Norm |
| title_short | Dim and Small Target Detection Based on Local Feature Prior and Tensor Train Nuclear Norm |
| title_sort | dim and small target detection based on local feature prior and tensor train nuclear norm |
| topic | Infrared target detection strong edge contours and strong noise tensor train nuclear norm |
| url | https://ieeexplore.ieee.org/document/10410248/ |
| work_keys_str_mv | AT anqingwu dimandsmalltargetdetectionbasedonlocalfeaturepriorandtensortrainnuclearnorm AT xiangsuofan dimandsmalltargetdetectionbasedonlocalfeaturepriorandtensortrainnuclearnorm AT leimin dimandsmalltargetdetectionbasedonlocalfeaturepriorandtensortrainnuclearnorm AT wenlinqin dimandsmalltargetdetectionbasedonlocalfeaturepriorandtensortrainnuclearnorm AT lingyu dimandsmalltargetdetectionbasedonlocalfeaturepriorandtensortrainnuclearnorm |