Ship historical track rule extraction method based on unsupervised clustering

Abstract

The invention discloses a ship historical track rule extraction method based on unsupervised clustering. The invention belongs to ship historical track rule extraction. According to the method, the clustering result is provided for sea area grid division and related statistical calculation, the purposes of noise track elimination and track pre-classification are achieved, and the final track abnormity detection precision is improved. According to the method, firstly, track points are compressed through a track thinning algorithm, then track line segments are clustered through a density-based spatial clustering algorithm (DBSCAN); on one hand, outlier abnormal track line segments are removed, and on the other hand, track line segments similar in position, course, speed and the like are combined into one class, so that separation of air routes is achieved. Finally, a de-noising and aggregated track cluster is formed for subsequent sea area grid division. The method solves the problem that in sea area grid training, the statistical result is influenced by the fact that routes cannot be distinguished and channels are staggered, and improves the accuracy of anomaly detection.

Description

technical field [0001] The invention belongs to a method for extracting a law of a ship's historical track, in particular to a method for extracting a law of a ship's historical track based on unsupervised clustering. Background technique [0002] Vessel Traffic System, Vessel Traffic System, is an information management system used to manage ship traffic and ensure safe navigation of ships. With the increase of human commercial production activities, the number of ships conducting surface operations is increasing. How to use the VTS system for effective service and supervision of more and more surface ships is a problem faced by various maritime departments. The VTS system will accumulate a large amount of ship track information every day. Taking Yantai as an example, there are hundreds of millions of AIS messages per month in 2017. Finding abnormal ship behavior from a large amount of ship information is laborious and difficult to achieve in an efficient and timely manner....

AI Technical Summary

Problems solved by technology

[0004] Using this statistics-based sea area grid training method can learn the laws of historical tracks to a certain extent, but there are two problems: 1) This method counts the track information of all ships, and there must be different ship types , the track points of ships on different routes are located in the same area, but the track rules of these ships should be different. If they are calculated uniformly, they will affect each other's statistical results and ultimately affect the detection accuracy; 2) Separate statistical grids The track points within split the correlation of track segments. For example, if there are two intersecting tracks, the number of track points at the intersecting position will be significantly higher than the number at other positions. If there are multiple track intersecting At this time, there is a risk of false positives in the way of sorting and calculating abnormalities by grid points

Images