The invention discloses a ship track prediction method and device. The method comprises the following steps: discretizing a track distribution range into a plurality of grid units in a ship navigation area based on the space-time distribution density of a ship track; acquiring a grid unit corresponding to the current ship trajectory node and adjacent grid units; respectively calculating a cost function of ship position transfer between the current grid unit and the adjacent grid unit; and taking the adjacent grid unit with the minimum cost function as the predicted ship track of ship position transfer. According to the scheme, reliability evaluation and real trajectory restoration are carried out on the original data of the training trajectory before prediction, time sequence factor constraints are added in the ship navigation network diagram, and the time sequence correlation of the trajectory data is considered while the spatial correlation of the adjacent trajectories is depicted. And flexibly setting the size of the grid unit in the ship navigation network based on the space-time distribution density of the ship trajectory.
本发明公开了一种船舶航迹预测方法及装置,在船舶航行区域内基于船舶轨迹的时空分布密度将航迹分布范围离散化为若干网格单元;获取当前船舶轨迹节点对应的网格单元及其相邻的网格单元;分别计算当前网格单元与相邻网格单元之间船位转移的成本函数;将所述成本函数最小的相邻网格单元作为预测的船位转移的船舶航迹。本发明方案在预测之前对训练轨迹原始数据进行可靠性评估与修复还原真实轨迹,在船舶航行网络图中添加时序因子约束,在刻画相邻轨迹的空间相关性的同时,兼顾航迹数据的时序相关性。基于船舶轨迹的时空分布密度灵活设置船舶航行网络中网格单元的大小。
Ship track prediction method and device
一种船舶航迹预测方法及装置
2023-01-13
Patent
Elektronische Ressource
Chinesisch
IPC: | G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Prediction of ship track based on ARIMA-LSTM
SPIE | 2022
|Europäisches Patentamt | 2017
|Prediction of ship track based on ARIMA-LSTM
British Library Conference Proceedings | 2022
|