Sea Clutter Suppression Method Based on Neural Networks

Aiming at the problem of low target signal-To-clutter ratio in the sea clutter environment, a sea clutter suppression method based on deep learning is proposed. Combining with the idea of segmentation and using an improved u-net framework, a network structure for sea clutter suppression is designed. The U-net network is integrated with the residual network, and the Inception module is used in the encoding part to replace the traditional convolution operation. First, the up-And-down sampling structure and jump connection are used to fuse complex multi-layer features. Secondly, by introducing the Inception module, features of different scales and abstract levels are captured, thereby enhancing the representation ability of the coding part. Finally, the actual data is used for the proposed method. Performance is evaluated. The results show that this method has a good effect on improving the target signal-To-clutter ratio and the stability of clutter suppression.