A method, system and electronic equipment for automatic behavior division based on ship trajectory

Abstract

The invention discloses a method, system and electronic equipment for automatic behavior division based on ship trajectories. The invention preprocesses multi-ship trajectory data and designs a division cost function, and conducts multi-ship common in the same channel at two levels of time and individual Behavior pattern discovery further divides the trajectory, and at the same time dynamically determines the optimal number of behavior patterns and division schemes to generate division results. In the present invention, by designing an automatic classification method for ship behavior based on multi-ship trajectories, the complete motion information of the ship (including longitude and latitude, speed over the ground, course over the ground, etc.) can be preserved, and it can be expanded with the increase of the number of ships and the time-space characteristics. , while avoiding manual parameter setting and adjustment, and realizing automatic behavior pattern recognition and division of ship trajectories.

Description

technical field [0001] The invention belongs to the field of computer big data processing, and relates to a ship behavior automatic division method, system and electronic equipment, in particular to a ship track-based automatic behavior division method, system and electronic equipment. Background technique [0002] During the voyage of the ship, the sensors carried on the ship will record the ship's trajectory data, and a lot of valuable information can be mined from these data, which can be applied to shipping management, ship collision avoidance and other fields. However, due to factors such as complex and changeable navigation environment and equipment failure, ship trajectories often have problems such as low sampling rate, many noise points, uneven particle size, and irregular changes, which bring difficulties to the processing and analysis of navigation trajectories. Therefore, it is necessary to identify the different behavior patterns existing in the ship's trajector...

AI Technical Summary

Problems solved by technology

However, these methods often only focus on one of the ship's motion parameters and trajectory space structure, and cannot retain the complete information of the ship's motion process, and need to manually adjust the model parameters

In addition, the traditional method focuses on the behavior division of a single ship trajectory, and cannot distinguish the common behavior patterns of multiple ships on the same customary route and the unique personalized behavior of some ships, and cannot adapt to the needs of complex and changeable navigation scenarios.

Images