Floating Small Target Detection Algorithm based on Features Fusion of Full Polarization Information in Sea Clutter

The detection of floating small targets in strong sea clutter is a difficult problem for radar detection. Traditional algorithms have poor detection performance in a single domain (time domain, Doppler domain, and time-frequency domain). Feature-based detection algorithms are an effective method for detecting floating small targets on the sea surface. This paper proposes a feature fusion detection algorithm based on full polarization information. This paper selects six features in the time domain and Doppler domain, and extracts six features based on full polarization information. This paper analyzes the separability of these features, and finally uses the PCA-based anomaly detector to detect target. It is verified on the IPIX radar data set. Compared with the existing six-feature PCA-based anomaly detector algorithm, the experimental results prove that the proposed algorithm has excellent detection performance.