With the rapid development of the global economy, maritime transportation has become much more convenient due to large capacities and low freight. However, this means the sea lanes are becoming more and more crowded, leading to high probabilities of marine accidents in complex maritime environments. According to relevant historical statistics, a large number of accidents have happened in water areas that lack high precision navigation data, which can be utilized to enhance navigation safety. The purpose of this work was to carry out ship route planning automatically, by mining historical big automatic identification system (AIS) data. It is well-known that experiential navigation information hidden in maritime big data could be automatically extracted using advanced data mining techniques; assisting in the generation of safe and reliable ship planning routes for complex maritime environments. In this paper, a novel method is proposed to construct a big data-driven framework for generating ship planning routes automatically, under varying navigation conditions. The method performs density-based spatial clustering of applications with noise first on a large number of ship trajectories to form different trajectory vector clusters. Then, it iteratively calculates its centerline in the trajectory vector cluster, and constructs the waterway network from the node-arc topology relationship among these centerlines. The generation of shipping route could be based on the waterway network and conducted by rasterizing the marine environment risks for the sea area not covered by the waterway network. Numerous experiments have been conducted on different AIS data sets in different water areas, and the experimental results have demonstrated the effectiveness of the framework of the ship route planning proposed in this paper.

中文翻译：

---

大数据驱动的复杂海上环境中自动生成航线规划

随着全球经济的快速发展，由于运力大，货运量少，海上运输变得更加便捷。但是，这意味着海道变得越来越拥挤，导致在复杂的海洋环境中发生海上事故的可能性很高。根据有关的历史统计资料，在缺乏高精度导航数据的水域发生了大量事故，可用于提高航行安全性。这项工作的目的是通过挖掘历史大型自动识别系统（AIS）数据来自动执行船舶路线计划。众所周知，可以使用先进的数据挖掘技术自动提取隐藏在海上大数据中的体验式导航信息。协助为复杂的海上环境生成安全可靠的船舶计划路线。本文提出了一种新颖的方法来构建大数据驱动的框架，以在变化的导航条件下自动生成船舶计划路线。该方法首先在大量船舶航迹上对噪声进行应用的基于密度的空间聚类，以形成不同的航迹矢量聚类。然后，在轨迹向量簇中迭代地计算其中心线，并根据这些中心线之间的节点-弧形拓扑关系构造水路网络。航路的生成可以基于水路网络，并通过栅格化水路网络未覆盖的海域的海洋环境风险来进行。