Rotation- and Scale-Invariant Shape Extraction from Vessel Trajectories for Human-In-The-Loop Monitoring

Maritime vessel monitoring is vital for ensuring navigational safety, protecting marine ecosystems, and enforcing regulations. We present a framework to support expert analysis and monitoring of vessel activities using Automatic Identification System (AIS) trajectory data. By extracting rotation- and scale-invariant shape signatures through a relative Hough transform, our system clusters and organizes subtrajectory patterns, enabling intuitive visual exploration. Experts interactively associate representative shapes with maritime events such as trawling or port visits, creating an event-to-shape map used for real-time detection in new trajectories. The framework's design allows efficient handling of geometric and motion dynamics, while facilitating the creation of labeled datasets to improve automated analysis. We demonstrate its effectiveness on a dataset of fishing vessels, highlighting its potential for scalable, human-in-the-loop maritime surveillance.