A machine learning approach to radar sea clutter suppression

The radar detection of small maritime targets requires special attention to the suppression of sea clutter returns that, in certain circumstances, may be difficult to discriminate from target returns. In this paper, the novel use of machine learning techniques is explored to address this familiar problem. A comparison of the results obtained using two machine learning techniques for the suppression of sea clutter is presented. Data for this experiment was gathered using an experimental S-band radar called NetRAD. This radar system was observing a coastal scene and the data collected was classified as either target or clutter using k-Nearest-Neighbour (kNN) and Support Vector Machine (SVM) algorithms. The results are presented as averaged probability of detection and probability of false alarm.