Intelligent navigation mark collision avoidance method and system

Abstract

The invention discloses an intelligent navigation mark collision avoidance method. Intelligent ship-navigation mark collision risk prediction and early warning are realized through ship track prediction, 3D scene construction and collision risk estimation. The method comprises the steps of predicting ship tracks, and predicting the ship positions, the heading directions and the tracks of the shipfeature points according to a ship feature point model, the real-time and historical ship positions and heading directions of the ship, wherein the ship tracks are predicted according to a Kalman filtering method; constructing a 3D scene, and performing three-dimensional visual display on the matched cloth of a navigation mark, the three-dimensional visual display including a navigation mark matched cloth schematic diagram; and collision risk estimation: calculating the nearest meeting distance between the navigation mark and the ship feature point model and the driving distance required for reaching the meeting point ship, estimating the collision risk in real time, and pre-judging whether the ship collides with the navigation mark or not. The invention further discloses a device based onthe method. The method and the device have the advantage that ship-navigation mark collision risk intelligent prediction and early warning can be effectively realized.

Description

technical field [0001] The invention relates to the technical field of ship track prediction, and relates to an intelligent collision avoidance method and system for navigation marks. Background technique [0002] In the prior art, in the field of ship navigation prediction and control, various intelligent prediction algorithms have been used to predict the ship's navigation track, thereby ensuring the safety of ship navigation. In the prior art, methods for predicting ship trajectories use Kalman filters for calculation. However, a traditional Kalman filter uses the same sampling time interval throughout the filtering process. However, because the AIS position update report interval varies with different ship speeds, the communication between the coast station and the buoy is blocked and the network delays, sometimes the correct position data may not be received, or the position report may not be updated in time. In the prior art, some self-adaptive mechanisms have been i...

AI Technical Summary

Problems solved by technology

However, the traditional Kalman filter uses the same sampling time interval throughout the filtering process

However, because the AIS position update report time interval varies with different ship speeds, communication congestion and network delay between coast stations and buoys, sometimes the correct position data may not be received, or the position report may not be updated in time

In the prior art, some self-adaptive mechanisms have been introduced into the Kalman filter to predict the ship's track, but there are still problems that the position data is not updated in time or the estimation error is large

[0003] In addition, in the existing technology, especially in the field of navigation aids and ship navigation prediction, there is a lack of methods for the visualization of navigation aids and the intelligent prediction and early warning of ship-to-navigation collision risks

Images