Scottish researchers develop AI system to ‘modernise’ weighing shipping vessels

A consortium of researchers in Scotland have developed a new artificial intelligence (AI) technology which is said to modernise the way that shipping vessels are weighed and checked for stability.  

The University of Edinburgh and naval architecture firm Tymor Marine, with funding from CENSIS, Scotland’s innovation centre for sensing, imaging, and Internet of Things (IoT) technologies, have created a machine vision tool, powered by deep learning, that will automate and better read the draught marks on ships.  

Draught marks, which are numbers on the side of vessels that help to indicate how much of the ship is under water, are currently measured and recorded by eye, a process that is based on a 2,000-year-old principle formulated by Greek scientist Archimedes.  

However, accurate measurements are not always recorded, due to factors like waves, fading markings, lighting, and marine growth. The new technology uses algorithms applied to video recordings of ships to accurately identify where the waterline reaches on a ship’s hull.  

The two main developers of the technology are continuing to develop it, with the aim of creating a smartphone app that allows seafarers to accurately record measurements and upload them to the cloud for real-time readings.  

Rosie Clegg, naval architect at Tymor Marine, said: “We had been trying to develop this technology for some time, but quickly found there was no off-the-shelf software. Through CENSIS, we found the expertise we needed at the University of Edinburgh to develop our own technology and bring innovation to what is, broadly speaking, a traditional industry.  

“Over the last twelve weeks, we have been able to prove that the concept behind the technology is feasible. Now we will focus on its different elements, train it with data we are now capturing with each visit to a vessel, and begin taking it to a commercial level. We are also exploring the possibility of applying it to drones, which would make the process even safer.”  

Dr Hakan Bilen, reader in the School of Informatics at the University of Edinburgh, added: “The algorithm we have created for Tymor Marine has been built on the recent advances in deep neural networks. The model takes in a video showing a ship’s hull and identifies where digits on the side of a vessel intersects the water line in a variety of different scenarios. We are continuing to build the database by introducing more manual annotations for training and also to improve various components in the method, which should only make it more accurate in the future.”  

Corinne Critchlow-Watton, project manager at CENSIS, said: “This project is a great example of a small Scottish business bringing innovation to solve a global challenge. It is incredible to think that the worldwide shipping industry still relies on principles developed in ancient Greece for such an important part of how it operates. Machine vision could bring a more accurate, consistent, and safer approach to stability and weight checks for vessels, which can only be hugely positive for the sector. It is particularly exciting to see this technology being developed here in Scotland.”