Fast Target Localization Method for FMCW MIMO Radar via VDSR Neural Network
The traditional frequency-modulated continuous wave (FMCW) multiple-input multiple-output (MIMO) radar two-dimensional (2D) super-resolution (SR) estimation algorithm for target localization has high computational complexity, which runs counter to the increasing demand for real-time radar imaging. I...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/10/1956 |
| _version_ | 1827692257626554368 |
|---|---|
| author | Jingyu Cong Xianpeng Wang Xiang Lan Mengxing Huang Liangtian Wan |
| author_facet | Jingyu Cong Xianpeng Wang Xiang Lan Mengxing Huang Liangtian Wan |
| author_sort | Jingyu Cong |
| collection | DOAJ |
| description | The traditional frequency-modulated continuous wave (FMCW) multiple-input multiple-output (MIMO) radar two-dimensional (2D) super-resolution (SR) estimation algorithm for target localization has high computational complexity, which runs counter to the increasing demand for real-time radar imaging. In this paper, a fast joint direction-of-arrival (DOA) and range estimation framework for target localization is proposed; it utilizes a very deep super-resolution (VDSR) neural network (NN) framework to accelerate the imaging process while ensuring estimation accuracy. Firstly, we propose a fast low-resolution imaging algorithm based on the Nystrom method. The approximate signal subspace matrix is obtained from partial data, and low-resolution imaging is performed on a low-density grid. Then, the bicubic interpolation algorithm is used to expand the low-resolution image to the desired dimensions. Next, the deep SR network is used to obtain the high-resolution image, and the final joint DOA and range estimation is achieved based on the reconstructed image. Simulations and experiments were carried out to validate the computational efficiency and effectiveness of the proposed framework. |
| first_indexed | 2024-03-10T11:18:47Z |
| format | Article |
| id | doaj.art-1d518442af1c41d6ad25effc9c38ebe5 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T11:18:47Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-1d518442af1c41d6ad25effc9c38ebe52023-11-21T20:09:19ZengMDPI AGRemote Sensing2072-42922021-05-011310195610.3390/rs13101956Fast Target Localization Method for FMCW MIMO Radar via VDSR Neural NetworkJingyu Cong0Xianpeng Wang1Xiang Lan2Mengxing Huang3Liangtian Wan4State Key Laboratory of Marine Resource Utilization in South China Sea, School of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaState Key Laboratory of Marine Resource Utilization in South China Sea, School of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaState Key Laboratory of Marine Resource Utilization in South China Sea, School of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaState Key Laboratory of Marine Resource Utilization in South China Sea, School of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaKey Laboratory for Ubiquitous Network and Service Software of Liaoning Province, School of Software, Dalian University of Technology, Dalian 116620, ChinaThe traditional frequency-modulated continuous wave (FMCW) multiple-input multiple-output (MIMO) radar two-dimensional (2D) super-resolution (SR) estimation algorithm for target localization has high computational complexity, which runs counter to the increasing demand for real-time radar imaging. In this paper, a fast joint direction-of-arrival (DOA) and range estimation framework for target localization is proposed; it utilizes a very deep super-resolution (VDSR) neural network (NN) framework to accelerate the imaging process while ensuring estimation accuracy. Firstly, we propose a fast low-resolution imaging algorithm based on the Nystrom method. The approximate signal subspace matrix is obtained from partial data, and low-resolution imaging is performed on a low-density grid. Then, the bicubic interpolation algorithm is used to expand the low-resolution image to the desired dimensions. Next, the deep SR network is used to obtain the high-resolution image, and the final joint DOA and range estimation is achieved based on the reconstructed image. Simulations and experiments were carried out to validate the computational efficiency and effectiveness of the proposed framework.https://www.mdpi.com/2072-4292/13/10/1956FMCW MIMO radarjoint DOA and range estimationVDSRNystrom |
| spellingShingle | Jingyu Cong Xianpeng Wang Xiang Lan Mengxing Huang Liangtian Wan Fast Target Localization Method for FMCW MIMO Radar via VDSR Neural Network Remote Sensing FMCW MIMO radar joint DOA and range estimation VDSR Nystrom |
| title | Fast Target Localization Method for FMCW MIMO Radar via VDSR Neural Network |
| title_full | Fast Target Localization Method for FMCW MIMO Radar via VDSR Neural Network |
| title_fullStr | Fast Target Localization Method for FMCW MIMO Radar via VDSR Neural Network |
| title_full_unstemmed | Fast Target Localization Method for FMCW MIMO Radar via VDSR Neural Network |
| title_short | Fast Target Localization Method for FMCW MIMO Radar via VDSR Neural Network |
| title_sort | fast target localization method for fmcw mimo radar via vdsr neural network |
| topic | FMCW MIMO radar joint DOA and range estimation VDSR Nystrom |
| url | https://www.mdpi.com/2072-4292/13/10/1956 |
| work_keys_str_mv | AT jingyucong fasttargetlocalizationmethodforfmcwmimoradarviavdsrneuralnetwork AT xianpengwang fasttargetlocalizationmethodforfmcwmimoradarviavdsrneuralnetwork AT xianglan fasttargetlocalizationmethodforfmcwmimoradarviavdsrneuralnetwork AT mengxinghuang fasttargetlocalizationmethodforfmcwmimoradarviavdsrneuralnetwork AT liangtianwan fasttargetlocalizationmethodforfmcwmimoradarviavdsrneuralnetwork |