A Sea-Surface Radar Target-Detection Method Based on an Improved U-Net and Its FPGA Implementation

Existing radar target-detection methods exhibit suboptimal performance when they are applied to sea-surface target detection. This is due to the difficulties in detecting weak targets and the interference from sea clutter, as well as to the inability of statistical models to accurately model sea-surface targets, which leads to degraded detection performance. With the development of artificial intelligence technologies, research based on deep learning methods has gained momentum in the field of radar target detection. Considering the complexity of neural networks and the real-time requirements of radar target-detection algorithms, this paper investigates a sea-surface radar target-detection method based on an improved U-Net network and its FPGA implementation, achieving real-time radar target detection without relying on GPUs. This paper first selected the lightweight U-Net network through a survey and analysis. The original U-Net network was then structurally optimized using network volume-reduction methods. Based on the characteristics of the network structure, optimization strategies such as pipelining and parallel processing, hybrid-layer design, and convolution-layer optimization were applied to the accelerator system. These optimizations reduced the system’s hardware-resource requirements and enabled the complete deployment of the network onto the accelerator system. The accelerator system was implemented using high-level synthesis (HLS) with modular and template-based design approaches. Experiments showed that the proposed method has significant advantages in improving detection probability, reducing false-alarm rates, and achieving real-time processing.