Ship AIS Data Mining and Processing Method in Bridge Waters of Inland River

摘要

AIS (automatic identify system) data is widely used to judge a ship's trajectory and the encounter status of the inland waterway ship and analyze the features of the ship's behavior. It usually contains multidimensional attributes including time attributes and speed attributes. Not all of the AIS devices are in good quality. They may lose, repeat, or delay the dynamic information and probably lead to unreliable messaging. On this basis, a trajectory similarity measure and clustering method to segment a scene into semantic regions is proposed to eliminate the negative effect caused by AIS. First, we encoded the trajectory. Next, we computed both the object position and its instantaneous velocity by the improved similarity measure method to find the distance between two trajectories. According to different spatial and velocity distributions, we applied the improved hierarchical clustering algorithm which chooses the longest trajectory as each cluster representation to cluster trajectories. In each cluster, trajectories were spatially close, had similar velocities of motion, and represented one type of the activity pattern. Finally, through experimentation in the Wuhan Yangtze River Bridge area, the results show that the method can distinguish different clusters reasonably and improve clustering effectiveness.