MOL Starts Test Of Vessel Image Recognition System Using AI Technology On Nippon Maru
It was announced by Mitsui O.S.K. Lines, Ltd. (MOL) that they will be developing a new vessel imagar recognition and recording system and the system’s installation for demonstration testing aboriad the cruise ship “Nippon Maru” jointly with SenseTime Japan Ltd. By incorporating MOL’s knowledge and putting in artificial iintelligence, the systems graphic recognition engine was developed which allows the engine to recognize surrounding vessels. The system uses a terminal equipped with graphic processing unit and ultra resolution cameras to recognize and then automatically record vessels.
At night and even during periods of poor visibility, the image recognition technology can detect small vessels that vessel automatic identification systems cannot recognize. The need for autonomous smart ships in the future makes MOL view advance image recognition as an underlying technology that is needed for automated watch keeping.
MOL also plans to carefully review the accumulated image data that the system automatically records. MOL will use it to enhance the image recognition engine’s analysis accuracy.
MOL positions the navigation support system featuring image recognition, such as the AR voyage information display system, which is already in practical use, as part of its challenge project, called the “FOCUS EYE” series. The company continues to develop and modify the system, which supports crewmembers’ watch-keeping while underway, to enhance safe operation and speed up the automation of watch-keeping, with the long-term goal of realizing autonomous smart ships.
MOL has moved ahead with advanced support of safe operation and reduction of its environmental impact, as set out in the “ISHIN NEXT – MOL SMART SHIP PROJECT -,” launched in November 2016, and aims to become the customers’ first choice as a logistics partner by applying information and communications technology (ICT) to improve service quality and efficiency.
PR Reference: vesselfinder
