A ship loitering detection method based on ais data

Abstract

The invention discloses a ship loitering detection method based on AIS data. The invention can detect the ship loitering behavior according to the acquired AIS track data of the ship and classify the ship loitering behavior for massive track data, and summarizes four typical types. Relationships between trajectories of anomalous behavior of ship motion and defined variables. According to the analysis of the relationship between the characteristics of the ship's trajectory and the statistical parameters, the abnormal wandering behavior of the ship is detected according to the distribution of the trajectory in the grid. After filtering and smoothing the ship's AIS trajectory, a global spatio-temporal grid index is established, and the ship's trajectory is gridded, and the abnormal movement of the ship is detected according to the characteristics of the abnormal behavior trajectory of the ship, and abnormal classification and alarm are carried out for the abnormal trajectory of the ship's motion behavior. Ship loitering behavior detection can provide decision support for maritime safety supervision, enhance maritime traffic safety, and ensure safe navigation of ships, which is of great significance to promote safe, efficient and smooth maritime transportation.

Description

technical field [0001] The invention relates to the field of big data analysis, in particular to a ship loitering detection method based on AIS data. Background technique [0002] In recent years, with the continuous increase in the number and density of ships at sea, the ship trajectory data has increased on a large scale. At the same time, the difficulty of maritime traffic safety management has also increased. It is necessary to conduct deeper analysis and processing of ship track data in order to enhance the safety of maritime traffic. . At present, more and more scholars use the data information provided by the equipment of the ship automatic identification system to conduct research on maritime traffic. [0003] According to the behavior of the ship's trajectory, when non-fishing ships have approximate loitering behavior, these abnormal behaviors are often related to drunk driving, hijacking, illegal fishing, piracy, and illegal measurement. Then its trajectory lengt...

AI Technical Summary

Problems solved by technology

The traditional detection of ship loitering behavior is not highly targeted, and cannot classify and detect abnormal ship behavior, such as approximately elliptical ship loitering trajectories, ship repeated round-trip trajectories, etc.

The analysis and processing of ship trajectory data also lacks a processing method for massive data. The whole process is time-consuming and labor-intensive, and the data processing results lack objectivity and reliability.

Images