Anomaly Detection Method of Ship Trajectory Based on Channel Model

Abstract

The invention discloses a ship track abnormality detection method based on a channel model, comprising the following steps: 1. Acquiring historical AIS data in a selected time interval; Step 2. Preprocessing the historical AIS data; 3. The waypoints and routes of the waterway model are respectively extracted from the AIS data, and the waypoints and routes are respectively regarded as the vertices and edges of the graph in graph theory to form the waterway model: Step 4. Weight the waterway model according to the time element, and get The final channel model; step 5, comparing the final channel model with the track to be detected, and judging whether the track is abnormal according to whether the track to be detected appears in the final channel model. By combining the advantages of the point-based algorithm and the trajectory-based algorithm, the invention fully excavates the historical rules of navigation in the hotspot area, and obtains the behavior patterns and spatio-temporal information left by the navigation trajectory; it can perform short-term abnormal monitoring and long-term monitoring Abnormal monitoring.

Description

technical field [0001] The invention relates to the technical field of ship data processing, in particular to a ship track abnormality detection method based on a channel model. Background technique [0002] In the context of the era of world economic globalization, trade among countries and regions has increased, and the maritime transportation industry has achieved prosperity and development. At the same time, the hidden dangers of maritime navigation safety have gradually become prominent. On the one hand, the current number of ships in the world is huge and increasing day by day, the variety of ships and the complex routes make it difficult to predict the movement behavior of ships, and there are unstable factors in the safety environment; on the other hand, due to the limited capacity of terminals and waterways, waterway traffic Congestion, overburdened routes, and the contradiction between the increasing number of ships have emerged, and the criss-crossing channels and...

AI Technical Summary

Problems solved by technology

[0013] Generally speaking, it is easy to implement anomaly monitoring for ships with complete trajectories, but due to the changeable marine environment, especially in remote sea areas, the communication mechanism is not smooth, and real-time and continuous AIS data cannot be obtained, most algorithms are difficult. To achieve a satisfactory application effect

Images