The invention relates to a civil ship trajectory behavior analysis optimization method based on deep learning, belongs to the field of ship trajectory analysis, and solves the problem that civil ship trajectory behaviors cannot be analyzed only by using AIS data in the prior art. The method comprises the following steps: acquiring AIS data of a to-be-analyzed civil ship, weather information of a place where the to-be-analyzed civil ship is located and image information including a sea area where the to-be-analyzed civil ship is located; and preprocessing the AIS data, the weather information and the image information of the sea area to obtain four groups of vectors, namely an AIS information vector, a weather information vector, a marine traffic busy degree vector and a civil ship draft vector, and inputting the four groups of vectors into the trained civil ship trajectory analysis model to obtain a civil ship trajectory analysis result. Precise analysis of the civil ship trajectory is realized, and collision with other ships or navigation obstruction is avoided.
本发明涉及一种基于深度学习的民船轨迹行为分析优化方法,属于船舶轨迹分析领域,解决了现有技术中仅使用AIS数据无法分析民船轨迹行为的问题。方法包括:获取待分析民船的AIS数据、待分析民船所在地的天气信息以及包括待分析民船所在海域的图像信息;对AIS数据、天气信息及海域的图像信息进行预处理,得到四组向量,分别为:AIS信息向量、天气信息向量、海上交通繁忙度向量以及民船吃水量向量,将四组向量输入训练好的民船轨迹分析模型得到民船轨迹分析结果。实现了精准分析民船轨迹,避免与其他船只发生碰撞或阻碍航行。
Deep learning-based civil ship trajectory behavior analysis optimization method
基于深度学习的民船轨迹行为分析优化方法
2023-11-03
Patent
Elektronische Ressource
Chinesisch
IPC: | G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Navigation trajectory feature-based ship abnormal behavior identification method
Europäisches Patentamt | 2022
|Ship route prediction method based on ship trajectory clustering
Europäisches Patentamt | 2021
|