Ship detection algorithms in Synthetic Aperture Radar (SAR) imagery are broadly categorized into: (i) those that interpret sea clutter according to a pre-defined Probability Density Function (PDF), detecting anomalies in positions within the tail of the PDF based on a specified Probability of False Alarm (PFA); and (ii) those which utilize a sufficiently large training dataset to learn the decision boundary between the target and clutter classes. Despite numerous publications in both categories, a proper quantitative comparison of their performance is lacking. This study is a step towards crossing this chasm by conducting a direct comparison between two real-world representatives: (i) SUMO's K-distribution Constant False Alarm Rate (K-CFAR/SUMO) detector, and (ii) the Deep Learning Model that topped the xView3 (1 st DLM/xView3) challenge organized by the Defense Innovation Unit and Global Fishing Watch. The performance of both algorithms is characterized by tracking the number of False Alarms (FAs) and Missed Detections (MDs) in three labeled Sentinel-1A repeat-pass SAR images acquired in the Gulf of Guinea. The results demonstrate that 1 st DLM/xView3 outperforms K-CFAR/SUMO, achieving the best FAs-MDs trade-off.This paper is accepted for oral presentation in IEEE IGARSS 2024, Athens, Greece.

False alarms (FAs) pose a major challenge for operational ship detection in spaceborne Synthetic Aperture Radar (SAR) imagery. This paper presents a novel algorithm for identification and tracking of FAs in repeat-pass Radar Constellation Mission (RCM) imagery. The algorithm benefits from that not only ambiguities but also fixed ocean structures and small islands are recurrently detected at predetermined geographic locations in the repeat-pass acquisitions. Efficacy of the proposed algorithm is demonstrated through tracking an azimuth ambiguity, a small island, and an elevation grating lobe range ambiguity in a stack of twenty-six Ship Detection RCM images acquired near Galapagos Islands.