Abstract

Marine radar is widely employed in ocean monitoring systems. However, the presence of sea clutter and noise significantly hampers the detection performance of marine radar. In this paper, we propose an unsupervised-to-supervised sea clutter suppression and denoise framework. The unsupervised stage provides sufficiently high-quality pseudo-labels to the supervised stage, effectively addressing the challenge of obtaining clean labels in current supervised deep learning-based (DL-based) sea clutter suppression methods. The experiments demonstrate that our proposed method exhibits excellent adaptability in both single-target and multi-target scenarios, as well as under various pulse quantities, effectively suppressing sea clutter and noise in low signal-to-clutter ratio (SCR) and signal-to-noise ratio (SNR). In addition, we also verified that the proposed method does not lose clean signals at high SCR and SNR. To validate the widespread applicability of our unsupervised stage, we integrate it into other supervised DL-based clutter suppression methods, and the experiments show a noticeable improvement in the performance of these methods. To further verify the effectiveness of the proposed framework, we conduct validation on downstream applications of radar target detection. Our code will be released after possible acceptance.