Deep Unfolding Based Space-Time Adaptive Processing Method for Airborne Radar
The Sparse Recovery Space-Time Adaptive Processing (SR-STAP) method can use a small number of training range cells to effectively suppress the clutter of airborne radar. The SR-STAP approach may successfully eliminate airborne radar clutter using a limited number of training range cells. However, pr...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
China Science Publishing & Media Ltd. (CSPM)
2022-08-01
|
| Series: | Leida xuebao |
| Subjects: | |
| Online Access: | https://radars.ac.cn/cn/article/doi/10.12000/JR22051 |
| _version_ | 1797423492360044544 |
|---|---|
| author | Hangui ZHU Weike FENG Cunqian FENG Bo ZOU Fuyu LU |
| author_facet | Hangui ZHU Weike FENG Cunqian FENG Bo ZOU Fuyu LU |
| author_sort | Hangui ZHU |
| collection | DOAJ |
| description | The Sparse Recovery Space-Time Adaptive Processing (SR-STAP) method can use a small number of training range cells to effectively suppress the clutter of airborne radar. The SR-STAP approach may successfully eliminate airborne radar clutter using a limited number of training range cells. However, present SR-STAP approaches are all model-driven, limiting their practical applicability due to parameter adjustment difficulties and high computational cost. To address these problems, this study, for the first time, introduces the Deep Unfolding/Unrolling (DU) method to airborne radar clutter reduction and target recognition by merging the model-driven SR method and the data-driven deep learning method. Firstly, a combined estimation model for clutter space-time spectrum and Array Error (AE) parameters is established and solved using the Alternating Direction Method of Multipliers (ADMM) algorithm. Secondly, the ADMM algorithm is unfolded to a deep neural network, named AE-ADMM-Net, to optimize all iteration parameters using a complete training dataset. Finally, the training range cell data is processed by the trained AE-ADMM-Net, jointly estimating the clutter space-time spectrum and the radar AE parameters efficiently and accurately. Simulation results show that the proposed DU-STAP method can achieve higher clutter suppression performance with lower computational cost compared to typical SR-STAP methods. |
| first_indexed | 2024-03-09T07:48:36Z |
| format | Article |
| id | doaj.art-5c5eb59cece441fe8eebf8d0453dba0e |
| institution | Directory Open Access Journal |
| issn | 2095-283X |
| language | English |
| last_indexed | 2024-03-09T07:48:36Z |
| publishDate | 2022-08-01 |
| publisher | China Science Publishing & Media Ltd. (CSPM) |
| record_format | Article |
| series | Leida xuebao |
| spelling | doaj.art-5c5eb59cece441fe8eebf8d0453dba0e2023-12-03T02:20:09ZengChina Science Publishing & Media Ltd. (CSPM)Leida xuebao2095-283X2022-08-0111467669110.12000/JR22051R22051Deep Unfolding Based Space-Time Adaptive Processing Method for Airborne RadarHangui ZHU0Weike FENG1Cunqian FENG2Bo ZOU3Fuyu LU4Air and Missile Defense College, Air Force Engineering University, Xi’an 710051, ChinaAir and Missile Defense College, Air Force Engineering University, Xi’an 710051, ChinaAir and Missile Defense College, Air Force Engineering University, Xi’an 710051, ChinaAir and Missile Defense College, Air Force Engineering University, Xi’an 710051, ChinaAir and Missile Defense College, Air Force Engineering University, Xi’an 710051, ChinaThe Sparse Recovery Space-Time Adaptive Processing (SR-STAP) method can use a small number of training range cells to effectively suppress the clutter of airborne radar. The SR-STAP approach may successfully eliminate airborne radar clutter using a limited number of training range cells. However, present SR-STAP approaches are all model-driven, limiting their practical applicability due to parameter adjustment difficulties and high computational cost. To address these problems, this study, for the first time, introduces the Deep Unfolding/Unrolling (DU) method to airborne radar clutter reduction and target recognition by merging the model-driven SR method and the data-driven deep learning method. Firstly, a combined estimation model for clutter space-time spectrum and Array Error (AE) parameters is established and solved using the Alternating Direction Method of Multipliers (ADMM) algorithm. Secondly, the ADMM algorithm is unfolded to a deep neural network, named AE-ADMM-Net, to optimize all iteration parameters using a complete training dataset. Finally, the training range cell data is processed by the trained AE-ADMM-Net, jointly estimating the clutter space-time spectrum and the radar AE parameters efficiently and accurately. Simulation results show that the proposed DU-STAP method can achieve higher clutter suppression performance with lower computational cost compared to typical SR-STAP methods.https://radars.ac.cn/cn/article/doi/10.12000/JR22051space-time adaptive processing (stap)sparse recoverydeep learningdeep unfolding/unrolling (du)array error |
| spellingShingle | Hangui ZHU Weike FENG Cunqian FENG Bo ZOU Fuyu LU Deep Unfolding Based Space-Time Adaptive Processing Method for Airborne Radar Leida xuebao space-time adaptive processing (stap) sparse recovery deep learning deep unfolding/unrolling (du) array error |
| title | Deep Unfolding Based Space-Time Adaptive Processing Method for Airborne Radar |
| title_full | Deep Unfolding Based Space-Time Adaptive Processing Method for Airborne Radar |
| title_fullStr | Deep Unfolding Based Space-Time Adaptive Processing Method for Airborne Radar |
| title_full_unstemmed | Deep Unfolding Based Space-Time Adaptive Processing Method for Airborne Radar |
| title_short | Deep Unfolding Based Space-Time Adaptive Processing Method for Airborne Radar |
| title_sort | deep unfolding based space time adaptive processing method for airborne radar |
| topic | space-time adaptive processing (stap) sparse recovery deep learning deep unfolding/unrolling (du) array error |
| url | https://radars.ac.cn/cn/article/doi/10.12000/JR22051 |
| work_keys_str_mv | AT hanguizhu deepunfoldingbasedspacetimeadaptiveprocessingmethodforairborneradar AT weikefeng deepunfoldingbasedspacetimeadaptiveprocessingmethodforairborneradar AT cunqianfeng deepunfoldingbasedspacetimeadaptiveprocessingmethodforairborneradar AT bozou deepunfoldingbasedspacetimeadaptiveprocessingmethodforairborneradar AT fuyulu deepunfoldingbasedspacetimeadaptiveprocessingmethodforairborneradar |