MOL begins testing of vessel image recognition tech

Mitsui O.S.K. Lines (MOL) reports that it has developed a new vessel image recognition and recording system in conjunction with Kyoto-based company SenseTime Japan, which has now been installed on board the cruise ship Nippon Maru for demonstration testing.

The image recognition technology can detect small vessels that are not recognisable by vessel automatic identification systems (AIS), the company said, and can be used at night or during other periods of poor visibility to improve situational awareness.

The system’s graphic recognition engine builds on MOL’s previous work in the area of applying artificial intelligence (AI) and deep learning technology to allow computers to identify vessels in its vicinity.

The technology installed on the Nippon Maru has been programmed to recognise and automatically record nearby vessels using a terminal equipped with a graphic processing unit (GPU) and ultrahigh-resolution cameras. The data collected by the system during operations can then be fed back into the AI application to further enhance the accuracy of the image recognition engine in the future, meaning that it should continuously improve over time.

The development of this technology forms part of MOL’s ongoing FOCUS project to support vessel navigation through the use of image recognition and AR (augmented reality) voyage information displays, with AR systems having been already implemented on a number of the company’s ships.

Share this story

About the Author

Picture of Rob O'Dwyer
Rob O'Dwyer

Rob is Chief Network Officer and one of the founders of Smart Maritime Network. He also serves as Chairman of the Smart Maritime Council. Rob has worked in the maritime technology sector since 2005, managing editorial for a range of leading publications in the transport and logistics sector. Get in touch by email by clicking here, or on LinkedIn by clicking here.

Further Reading

News Archive