11 August 2023 in Computers in Biology and Medicine
30 March 2026 in IEEE Transactions on Aerospace and Electronic Systems
This paper presents a maritime target detection framework termed Multi-Domain Features Guided Supervised Contrastive Learning (MDFG_SCL), which integrates physically interpretable statistical features with deep feature representations within a supervised contrastive learning framework. To further enhance the discriminative capability of the shallow features, the Gini Index is calculated for different candidate features to evaluate their separability between clutter and target echoes, and these features are then adaptively combined through a weighted strategy. Specifically, in the wavelet domain, two effective features are designed, where radar echoes are processed through wavelet decomposition to extract the Wavelet Approximation Energy Ratio and Wavelet Entropy, which characterize signal energy distribution and complexity. These features, along with additional domain-specific components, are incorporated as structured priors to guide the representation learning of a convolutional neural network. This fusion enhances the model's ability to distinguish between sea clutter and target echoes. Experimental results on both simulated and real radar datasets demonstrate that the proposed method significantly improves detection probability and enhances generalization performance across diverse maritime environments.