Nonhomogeneous Sea Clutter Suppression Using Complex-Valued U-Net Model

doi:10.1109/LGRS.2022.3214633

Nonhomogeneous Sea Clutter Suppression Using Complex-Valued U-Net Model

2022-01-01

21

PRE

AI

DOI：10.1109/LGRS.2022.3214633

Original

Original request for help

Save

Abstract

En 中文

This letter considers the problem of target detection in the nonhomogeneous sea clutter environment and proposes the complex-valued U-Net (CV-UNet)-based clutter suppression method. Specifically, first, the complex signal features of radar echo sequences are extracted by developing the complex-valued convolutional blocks. Second, the complex multilevel features are fused, by employing the up-down sampling structure and skip connections, to suppress nonhomogeneous sea clutter. Furthermore, the false alarm controllable detector is designed to detect the targets. Finally, the performance of the proposed method is evaluated via real data. The results show that it has a higher detection probability compared with the real-valued U-Net (RV-UNet).

Keywords:

Complex-valued U-Net (CV-UNet)

deep learning

marine target detection

sea clutter suppression

Nonhomogeneous Sea Clutter Suppression Using Complex-Valued U-Net Model

Abstract

Journal

Organization