Polar Cluster-Based Target Tracking for Maritime Radar Applications
Paes Moreira, Lucas, Michailas Romanovas · elib (German Aerospace Center) · 2026
Accurate maritime situational awareness is essential for safety, security, and environmental protection. While the Automatic Identification System (AIS) is widely used, it is vulnerable to jamming/spoofing as well as and intentional manipulation. These limitations can be mitigated through independent validation using marine X-band radar, where high-resolution coastal sensors detect extended targets with distance-dependent sparsity and raw data in polar coordinates. This paper evaluates a polar-domain clustering algorithm and its impact on extended-object multi-target tracking (MTT) algorithms, evaluating in several frameworks of different complexity. A Random Matrix Model (RMM) incorporating radar intensity improves estimation of target centroid and extent, enhancing vessel shape representation compared to spatial-only approaches. Performance is validated on real-world X-band radar data within selected Regions of Interest (ROI) and different distances from the sensor, where objects have different point cloud spatial densities. Results show that data clustering in polar domain is more robust against the distance variability of detections w.r.t. the sensor and benefits the performance of the tracking algorithms.