Target Detection in Maritime Radar Tracking Based on Spatial Image Gradients

This article presents a target detection algorithm based on spatial gradient image features to enhance radar detection performance in low <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">signal-to-noise ratio</i> (SNR) environments. The proposed <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">spatial gradient-based detector</i> (SGBD) exploits the characteristic appearance patterns of targets in radar imagery without requiring specific target feature functions. The algorithm calculates intensity variations across the image and imposes a smoothing constraint to account for target features without knowing the specific target model. The discrete implementation employs a convolution kernel to approximate gradients and Laplacians alongside an iterative solution to the Euler-Lagrange equation. The performance is evaluated against standard <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">constant false alarm rate</i> (CFAR) detectors using Monte Carlo simulations, highlighting the advantages of the proposed approach. The simulations further address the impact of heavy-tailed clutter distributions and spatially correlated clutter, as commonly encountered in maritime scenarios. In addition, real-world maritime radar data results are shown to validate the SGBD’s effectiveness.