Toward Enhanced Support for Ship Sailing

Abstract

Ship sailing is a complex endeavour, requiring carefully considered proactive and reactive strategies in choosing the course of action that best suits the various events to be managed. Humans are already supported by different technologies for sailing, however these technologies are usually available in isolation. In this paper we show how to use simultaneously three different technologies by fusing their information in order to provide enhanced support for ship sailing. To the best of our knowledge no similar approach is reported in the literature from an operational point of view. In particular, we show how to fuse the video acquired from a camera with the information available from a radar/Lidar and an AIS receiver. The video frames are analyzed in order to automatically detect surrounding ships and seamarks, the Lidar is used to determine the average or minimum distance from the ship to the acquired targets and finally the AIS receiver logs are queried to determine, if available, useful information related to the surrounding ships, such as their geographic location, type of ship etc. Our experimental results are promising and encouraging. We believe that the simultaneous use of these technologies is a step towards fully autonomous ship sailing.

Keywords

• Ship detection
• deep learning
• lidar
• AIS receiver
• situation awareness
• image processing