A Multistage Detection Framework Based on TFA and Multiframe Correlation for HFSWR
Maritime surveillance heavily relies on high-frequency surface wave radar (HFSWR) systems. However, clutter and interference make it difficult to accurately detect vessel targets using a single-frame detection method. This study introduces an improved time-frequency analysis (TFA) algorithm to enhan...
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/10834597/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586872573919232 |
|---|---|
| author | Zongtai Li Gangsheng Li Ling Zhang Lanjun Liu Q. M. Jonathan Wu |
| author_facet | Zongtai Li Gangsheng Li Ling Zhang Lanjun Liu Q. M. Jonathan Wu |
| author_sort | Zongtai Li |
| collection | DOAJ |
| description | Maritime surveillance heavily relies on high-frequency surface wave radar (HFSWR) systems. However, clutter and interference make it difficult to accurately detect vessel targets using a single-frame detection method. This study introduces an improved time-frequency analysis (TFA) algorithm to enhance the features in single-frame detection. In this article, TFA, multiframe correlation, and deep neural networks are integrated to develop a three-stage detection framework. First, faster R-CNN is customized for the preprocessing stage to identify sea clutter regions. Then, based on the range-Doppler (RD) spectrum, suspicious targets are swiftly identified amidst clutter in the initial stage. Subsequently, the improved TFA algorithm is applied to adjacent range cells of suspicious targets to generate multiframe TF images, forming a three-dimensional data block structured as time-RD frequency. To reduce computational complexity, a TFA method using multisynchrosqueezing transform is employed, enhancing detection accuracy for targets within cluttered regions. In the final stage, a 3DResnet model is utilized to leverage the differences in features between clutter and targets across three dimensions. This allows for distinguishing genuine targets from false targets using time series information from multiple frames. Comparative analysis against classical target detection algorithms demonstrates the superior detection performance of the proposed framework within clutter regions. This showcases its potential for enhancing the maritime surveillance capabilities of HFSWR. |
| format | Article |
| id | doaj-art-87d28ea65ab440ab82cbd16783d4b743 |
| 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-87d28ea65ab440ab82cbd16783d4b7432025-01-25T00:00:09ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183893390410.1109/JSTARS.2025.352746810834597A Multistage Detection Framework Based on TFA and Multiframe Correlation for HFSWRZongtai Li0https://orcid.org/0009-0003-1022-8893Gangsheng Li1Ling Zhang2https://orcid.org/0000-0002-1679-7128Lanjun Liu3https://orcid.org/0000-0001-7650-9098Q. M. Jonathan Wu4https://orcid.org/0000-0002-5208-7975College of Engineering, Ocean University of China, Qingdao, ChinaDepartment of Education, Ocean University of China, Qingdao, ChinaCollege of Engineering, Ocean University of China, Qingdao, ChinaCollege of Engineering, Ocean University of China, Qingdao, ChinaDepartment of Electrical and Computer Engineering, University of Windsor, Windsor, ON, CanadaMaritime surveillance heavily relies on high-frequency surface wave radar (HFSWR) systems. However, clutter and interference make it difficult to accurately detect vessel targets using a single-frame detection method. This study introduces an improved time-frequency analysis (TFA) algorithm to enhance the features in single-frame detection. In this article, TFA, multiframe correlation, and deep neural networks are integrated to develop a three-stage detection framework. First, faster R-CNN is customized for the preprocessing stage to identify sea clutter regions. Then, based on the range-Doppler (RD) spectrum, suspicious targets are swiftly identified amidst clutter in the initial stage. Subsequently, the improved TFA algorithm is applied to adjacent range cells of suspicious targets to generate multiframe TF images, forming a three-dimensional data block structured as time-RD frequency. To reduce computational complexity, a TFA method using multisynchrosqueezing transform is employed, enhancing detection accuracy for targets within cluttered regions. In the final stage, a 3DResnet model is utilized to leverage the differences in features between clutter and targets across three dimensions. This allows for distinguishing genuine targets from false targets using time series information from multiple frames. Comparative analysis against classical target detection algorithms demonstrates the superior detection performance of the proposed framework within clutter regions. This showcases its potential for enhancing the maritime surveillance capabilities of HFSWR.https://ieeexplore.ieee.org/document/10834597/3DResNetdeep learninghigh-frequency surface wave radar (HFSWR)target detectiontime-frequency analysis (TFA) |
| spellingShingle | Zongtai Li Gangsheng Li Ling Zhang Lanjun Liu Q. M. Jonathan Wu A Multistage Detection Framework Based on TFA and Multiframe Correlation for HFSWR IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 3DResNet deep learning high-frequency surface wave radar (HFSWR) target detection time-frequency analysis (TFA) |
| title | A Multistage Detection Framework Based on TFA and Multiframe Correlation for HFSWR |
| title_full | A Multistage Detection Framework Based on TFA and Multiframe Correlation for HFSWR |
| title_fullStr | A Multistage Detection Framework Based on TFA and Multiframe Correlation for HFSWR |
| title_full_unstemmed | A Multistage Detection Framework Based on TFA and Multiframe Correlation for HFSWR |
| title_short | A Multistage Detection Framework Based on TFA and Multiframe Correlation for HFSWR |
| title_sort | multistage detection framework based on tfa and multiframe correlation for hfswr |
| topic | 3DResNet deep learning high-frequency surface wave radar (HFSWR) target detection time-frequency analysis (TFA) |
| url | https://ieeexplore.ieee.org/document/10834597/ |
| work_keys_str_mv | AT zongtaili amultistagedetectionframeworkbasedontfaandmultiframecorrelationforhfswr AT gangshengli amultistagedetectionframeworkbasedontfaandmultiframecorrelationforhfswr AT lingzhang amultistagedetectionframeworkbasedontfaandmultiframecorrelationforhfswr AT lanjunliu amultistagedetectionframeworkbasedontfaandmultiframecorrelationforhfswr AT qmjonathanwu amultistagedetectionframeworkbasedontfaandmultiframecorrelationforhfswr AT zongtaili multistagedetectionframeworkbasedontfaandmultiframecorrelationforhfswr AT gangshengli multistagedetectionframeworkbasedontfaandmultiframecorrelationforhfswr AT lingzhang multistagedetectionframeworkbasedontfaandmultiframecorrelationforhfswr AT lanjunliu multistagedetectionframeworkbasedontfaandmultiframecorrelationforhfswr AT qmjonathanwu multistagedetectionframeworkbasedontfaandmultiframecorrelationforhfswr |