Abnormal Detection Method of Transship Based on Marine Target Spatio-Temporal Data

Abstract

Marine target situational awareness is developing towards intelligence. The practical application of marine law enforcement, route control, fishery supervision and other fields makes marine ship track mining and anomaly analysis a hot direction of technology development. At present, most of the research focuses on the feature recognition of single target or single target signal, while the research on correlation anomaly detection based on multi target or multi target signal is relatively less. In this paper, based on the large spatio-temporal data of ocean targets such as radar and AIS track, the corresponding recognition algorithm is designed for the abnormal transport behavior. The real-time batch detection of illegal transshipment is realized, which verifies the effectiveness of the algorithm and shows good performance in practical application scenarios.