Data‐driven sampling pattern design for sparse spotlight SAR imaging
Abstract This paper proposes a joint optimization method for the imaging algorithm and sampling scheme of sparse spotlight synthetic aperture radar (SAR) imaging based on deep convolutional neural networks. Traditional compressed sensing‐based sparse SAR imaging has been widely studied. Deep learnin...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-11-01
|
| Series: | Electronics Letters |
| Online Access: | https://doi.org/10.1049/ell2.12650 |
| _version_ | 1811179856808902656 |
|---|---|
| author | Yao Zhao Wenkun Huang Xiangyin Quan Wing‐Kuen Ling Zhe Zhang |
| author_facet | Yao Zhao Wenkun Huang Xiangyin Quan Wing‐Kuen Ling Zhe Zhang |
| author_sort | Yao Zhao |
| collection | DOAJ |
| description | Abstract This paper proposes a joint optimization method for the imaging algorithm and sampling scheme of sparse spotlight synthetic aperture radar (SAR) imaging based on deep convolutional neural networks. Traditional compressed sensing‐based sparse SAR imaging has been widely studied. Deep learning and sparse unfolding networks have been introduced into sparse SAR imaging, but most current works focus only on the imaging stage and simply adopt the conventional uniform or random downsampling scheme. Considering that the imaging quality also depends on the sampling pattern besides the imaging algorithm, this paper introduces a learning‐based strategy to jointly optimize the sampling scheme and the imaging network parameters of the reconstruction module. In a deep learning‐based image reconstruction scheme, joint and continuous optimization of the sampling patterns and convolutional neural network parameters is achieved to improve the image quality. Simulation results based on real SAR image data set illustrate the effectiveness and superiority of the proposed framework. |
| first_indexed | 2024-04-11T06:41:36Z |
| format | Article |
| id | doaj.art-8c66f44e508e45329866f7c1e79bbdec |
| institution | Directory Open Access Journal |
| issn | 0013-5194 1350-911X |
| language | English |
| last_indexed | 2024-04-11T06:41:36Z |
| publishDate | 2022-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | Electronics Letters |
| spelling | doaj.art-8c66f44e508e45329866f7c1e79bbdec2022-12-22T04:39:31ZengWileyElectronics Letters0013-51941350-911X2022-11-01582492092310.1049/ell2.12650Data‐driven sampling pattern design for sparse spotlight SAR imagingYao Zhao0Wenkun Huang1Xiangyin Quan2Wing‐Kuen Ling3Zhe Zhang4Guangdong University of Technology Guangzhou ChinaGuangdong University of Technology Guangzhou ChinaChina Academy of Launch Vehicle Technology Beijing ChinaGuangdong University of Technology Guangzhou ChinaSuzhou Aerospace Information Research Institute Suzhou ChinaAbstract This paper proposes a joint optimization method for the imaging algorithm and sampling scheme of sparse spotlight synthetic aperture radar (SAR) imaging based on deep convolutional neural networks. Traditional compressed sensing‐based sparse SAR imaging has been widely studied. Deep learning and sparse unfolding networks have been introduced into sparse SAR imaging, but most current works focus only on the imaging stage and simply adopt the conventional uniform or random downsampling scheme. Considering that the imaging quality also depends on the sampling pattern besides the imaging algorithm, this paper introduces a learning‐based strategy to jointly optimize the sampling scheme and the imaging network parameters of the reconstruction module. In a deep learning‐based image reconstruction scheme, joint and continuous optimization of the sampling patterns and convolutional neural network parameters is achieved to improve the image quality. Simulation results based on real SAR image data set illustrate the effectiveness and superiority of the proposed framework.https://doi.org/10.1049/ell2.12650 |
| spellingShingle | Yao Zhao Wenkun Huang Xiangyin Quan Wing‐Kuen Ling Zhe Zhang Data‐driven sampling pattern design for sparse spotlight SAR imaging Electronics Letters |
| title | Data‐driven sampling pattern design for sparse spotlight SAR imaging |
| title_full | Data‐driven sampling pattern design for sparse spotlight SAR imaging |
| title_fullStr | Data‐driven sampling pattern design for sparse spotlight SAR imaging |
| title_full_unstemmed | Data‐driven sampling pattern design for sparse spotlight SAR imaging |
| title_short | Data‐driven sampling pattern design for sparse spotlight SAR imaging |
| title_sort | data driven sampling pattern design for sparse spotlight sar imaging |
| url | https://doi.org/10.1049/ell2.12650 |
| work_keys_str_mv | AT yaozhao datadrivensamplingpatterndesignforsparsespotlightsarimaging AT wenkunhuang datadrivensamplingpatterndesignforsparsespotlightsarimaging AT xiangyinquan datadrivensamplingpatterndesignforsparsespotlightsarimaging AT wingkuenling datadrivensamplingpatterndesignforsparsespotlightsarimaging AT zhezhang datadrivensamplingpatterndesignforsparsespotlightsarimaging |