Omega-KA-Net: A SAR Ground Moving Target Imaging Network Based on Trainable Omega-K Algorithm and Sparse Optimization
The ground moving target (GMT) is defocused due to unknown motion parameters in synthetic aperture radar (SAR) imaging. Although the conventional Omega-K algorithm (Omega-KA) has been proven to be applicable for GMT imaging, its disadvantages are slow imaging speed, obvious sidelobe interference, an...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/7/1664 |
| _version_ | 1797437851059617792 |
|---|---|
| author | Hongwei Zhang Jiacheng Ni Shichao Xiong Ying Luo Qun Zhang |
| author_facet | Hongwei Zhang Jiacheng Ni Shichao Xiong Ying Luo Qun Zhang |
| author_sort | Hongwei Zhang |
| collection | DOAJ |
| description | The ground moving target (GMT) is defocused due to unknown motion parameters in synthetic aperture radar (SAR) imaging. Although the conventional Omega-K algorithm (Omega-KA) has been proven to be applicable for GMT imaging, its disadvantages are slow imaging speed, obvious sidelobe interference, and high computational complexity. To solve the above problems, a SAR-GMT imaging network is proposed based on trainable Omega-KA and sparse optimization. Specifically, we propose a two-dimensional (2-D) sparse imaging model deducted from the Omega-KA focusing process. Then, a recurrent neural network (RNN) based on an iterative optimization algorithm is built to learn the trainable parameters of Omega-KA by an off-line supervised training method, and the solving process of the sparse imaging model is mapped to each layer of the RNN. The proposed trainable Omega-KA network (Omega-KA-net) forms a new GMT imaging method that can be applied to high-quality imaging under down-sampling and a low signal to noise ratio (SNR) while saving the imaging time substantially. The experiments of simulation data and measured data demonstrate that the Omega-KA-net is superior to the conventional algorithms in terms of GMT imaging quality and time. |
| first_indexed | 2024-03-09T11:28:36Z |
| format | Article |
| id | doaj.art-8fdbf227931243cf9f4fec2aa364ad2e |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T11:28:36Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8fdbf227931243cf9f4fec2aa364ad2e2023-11-30T23:57:12ZengMDPI AGRemote Sensing2072-42922022-03-01147166410.3390/rs14071664Omega-KA-Net: A SAR Ground Moving Target Imaging Network Based on Trainable Omega-K Algorithm and Sparse OptimizationHongwei Zhang0Jiacheng Ni1Shichao Xiong2Ying Luo3Qun Zhang4School of Information and Navigation, Air Force Engineering University, Xi’an 710077, ChinaSchool of Information and Navigation, Air Force Engineering University, Xi’an 710077, ChinaSchool of Information and Navigation, Air Force Engineering University, Xi’an 710077, ChinaSchool of Information and Navigation, Air Force Engineering University, Xi’an 710077, ChinaSchool of Information and Navigation, Air Force Engineering University, Xi’an 710077, ChinaThe ground moving target (GMT) is defocused due to unknown motion parameters in synthetic aperture radar (SAR) imaging. Although the conventional Omega-K algorithm (Omega-KA) has been proven to be applicable for GMT imaging, its disadvantages are slow imaging speed, obvious sidelobe interference, and high computational complexity. To solve the above problems, a SAR-GMT imaging network is proposed based on trainable Omega-KA and sparse optimization. Specifically, we propose a two-dimensional (2-D) sparse imaging model deducted from the Omega-KA focusing process. Then, a recurrent neural network (RNN) based on an iterative optimization algorithm is built to learn the trainable parameters of Omega-KA by an off-line supervised training method, and the solving process of the sparse imaging model is mapped to each layer of the RNN. The proposed trainable Omega-KA network (Omega-KA-net) forms a new GMT imaging method that can be applied to high-quality imaging under down-sampling and a low signal to noise ratio (SNR) while saving the imaging time substantially. The experiments of simulation data and measured data demonstrate that the Omega-KA-net is superior to the conventional algorithms in terms of GMT imaging quality and time.https://www.mdpi.com/2072-4292/14/7/1664synthetic aperture radar (SAR)ground moving target (GMT)sparse imagingrecurrent neural networks (RNN)Omega-K |
| spellingShingle | Hongwei Zhang Jiacheng Ni Shichao Xiong Ying Luo Qun Zhang Omega-KA-Net: A SAR Ground Moving Target Imaging Network Based on Trainable Omega-K Algorithm and Sparse Optimization Remote Sensing synthetic aperture radar (SAR) ground moving target (GMT) sparse imaging recurrent neural networks (RNN) Omega-K |
| title | Omega-KA-Net: A SAR Ground Moving Target Imaging Network Based on Trainable Omega-K Algorithm and Sparse Optimization |
| title_full | Omega-KA-Net: A SAR Ground Moving Target Imaging Network Based on Trainable Omega-K Algorithm and Sparse Optimization |
| title_fullStr | Omega-KA-Net: A SAR Ground Moving Target Imaging Network Based on Trainable Omega-K Algorithm and Sparse Optimization |
| title_full_unstemmed | Omega-KA-Net: A SAR Ground Moving Target Imaging Network Based on Trainable Omega-K Algorithm and Sparse Optimization |
| title_short | Omega-KA-Net: A SAR Ground Moving Target Imaging Network Based on Trainable Omega-K Algorithm and Sparse Optimization |
| title_sort | omega ka net a sar ground moving target imaging network based on trainable omega k algorithm and sparse optimization |
| topic | synthetic aperture radar (SAR) ground moving target (GMT) sparse imaging recurrent neural networks (RNN) Omega-K |
| url | https://www.mdpi.com/2072-4292/14/7/1664 |
| work_keys_str_mv | AT hongweizhang omegakanetasargroundmovingtargetimagingnetworkbasedontrainableomegakalgorithmandsparseoptimization AT jiachengni omegakanetasargroundmovingtargetimagingnetworkbasedontrainableomegakalgorithmandsparseoptimization AT shichaoxiong omegakanetasargroundmovingtargetimagingnetworkbasedontrainableomegakalgorithmandsparseoptimization AT yingluo omegakanetasargroundmovingtargetimagingnetworkbasedontrainableomegakalgorithmandsparseoptimization AT qunzhang omegakanetasargroundmovingtargetimagingnetworkbasedontrainableomegakalgorithmandsparseoptimization |