BROWSE
Detail
Journal Article
Non-uniform virtual array position optimization for MIMO radar and neural network-based radar imaging enhancement
- Issue Date
- 2025-12
- Citation
- ETRI Journal, v.권호미정, pp.1-14
- ISSN
- 1225-6463
- Publisher
- 한국전자통신연구원
- Language
- English
- Type
- Journal Article
- Abstract
- This paper presents a method for enhancing the angular resolution of multiple input multiple output (MIMO) radar systems by employing an extended non-uniform virtual array. Although a larger aperture achieved through non-uniform antenna placement can enhance the resolution, it also introduces sidelobe artifacts that degrade the image quality. To construct a non-uniform array that minimizes the sidelobe effects, the MIMO antenna placement is optimized using a genetic algorithm. Additionally, a convolutional neural network is employed to further suppress residual sidelobe effects that remain after optimization. Notably, to reduce the time and cost associated with collecting large-scale training data, a simulation-based radar data generation method is introduced. Both simulation and real-world measurements using the TI AWR cascade radar module were conducted to validate the proposed method.
- KSP Keywords
- Convolution neural network(CNN), Data generation, MIMO Antenna, Multiple input multiple output (MIMO) radar, Network-based, Position optimization, Radar Data, Radar system, Real-world Measurement, Virtual array, angular resolution
This work is distributed under the term of Korea Open Government License (KOGL)
(Type 4: : Type 1 + Commercial Use Prohibition+Change Prohibition)
(Type 4: : Type 1 + Commercial Use Prohibition+Change Prohibition)
