Ship behavior track recognition method

Abstract

The invention discloses a ship behavior track recognition method. The method comprises the following steps of: obtaining a track of a ship according to a track parameter; carrying out region divisionon the current sea area in which the ship travels according to the geographic condition of the current sea area; dividing a sea area track section by using a corner method according to the divided seaarea, so as to obtain a plurality of ship sub-track fragment sets; carrying out error back propagation multilayer feed-forward network set clustering on the plurality of ship sub-track fragment sets,so as to obtain a typical ship behavior track mode; calculating a Hausdoff distance between a track of a to-be-recognized ship and the typical ship behavior track mode; setting a Hausdoff distance threshold value; and judging a behavior track mode of the to-be-recognized ship according to a comparison result between the Hausdoff distance and the Hausdoff distance threshold value, and if the Hausdoff distance is smaller than or equal to the Hausdoff distance threshold value, judging the behavior track mode of the ship as the typical ship behavior track mode. The method is capable of correctlyand rapidly judging behavior modes of ship tracks, avoiding the waste of offshore management resources and ensuring the personal and property safety of seamen.

Description

technical field [0001] The invention relates to the field of detection, in particular to a method for identifying ship behavior tracks. Background technique [0002] At present, the identification of abnormal behavior of ships is widely used in maritime intelligent traffic monitoring, which effectively prevents the occurrence of ship grounding and collision accidents, and is of great significance to ensure the safety of ship navigation. [0003] In some islands or other sea areas with dense obstacles, in order to avoid obstacles, the ship’s trajectory deviates from the conventional navigation, but such situations do not belong to abnormal ship behavior. Unnecessary waste of resources. Therefore, it is necessary to find new trajectory processing technology to improve the recognition technology under special conditions and promote the wide application of this technology in this field. [0004] The design of the existing ship trajectory recognition uses the vector autoregressi...

AI Technical Summary

Problems solved by technology

[0007] Since ships are easily affected by geographical conditions when operating at sea, the lengths of the trajectory segments according to the regional division are different, and there is no standard for dividing the sub-trajectory segments after the regional division. As a result, some common sub-patterns in the trajectory segments cannot be found, and it is easy to Ignore local features of the trajectory

Therefore, the error generated in the process of calculating the ship trajectory value is relatively large, which affects the recognition effect of ship behavior

[0008] 2. Poor application effect of ship trajectory value

[0009] Since the trajectory of the ship can be divided into several sub-trajectory segments, each sub-trajectory segment trajectory has a corresponding trajectory value, and the average value of the trajectory value is obtained by variance analysis of the trajectory values ​​of each segment of the ship. Due to too many uncertain factors at sea, it will affect The size of the trajectory value of each segment of the trajectory leads to the low sensitivity of the ship trajectory recognition model to the abnormality of the ship trajectory

Therefore, the practicality of this model is poor

Images