Radar Target Detection Under Correlated Non-Gaussian Clutter Using Transfer Learning

In radar signal processing, accurate detection of targets in the presence of noise and clutter is critical for systems like autonomous vehicles and military defense. This is due to the degradation of reflected signals by noise and clutter, which complicates target detection for radars. Recent advancements in deep learning, particularly convolutional neural networks and transfer learning, offer promising solutions for enhancing radar signal classification. This paper explores the integration of ResNet models for multi-target detection, comparing their performance with traditional constant false alarm rate algorithms and adaptive normalized matched filters in addressing correlated nonGaussian clutter and low signal-to-clutter-plus-noise ratios. Our method outperforms conventional and state-of-the-art techniques using pre-trained models with high nonlinear representation capability in terms of probability of detection, offering a robust solution for radar signal processing.