BSB Marine launches Oscar One – AI for sailors

The Oscar One Series combines a vision and processing unit in one to detect floating objects in a bid to reduce the risk of maritime collision.

The new design combines the vision and processing units, making the installation of this iteration of the navigational aid system straightforward.

Oscar – based on computer vision and artificial intelligence – can be installed on all types of professional craft in the boating and competition domain.

The system detects floating objects by day, as well as and, above all, by night, when the human eye is unable to see obstacles. With its day and night vision, Oscar therefore augments the crew’s vigilance 24/7 and boosts the safety of a vessel by reducing the risk of it colliding with floating objects, says BSB Marine.

The objects can be identifiable or not and are extremely diverse, including small non-signalled crafts, sleeping whales, wooden logs or simply floating objects.

Raphaël Biancale, a Franco-German automotive engineer, founder and CEO of the BSB Group, invented the product.

On his return from his first transatlantic passage in 2013, Biancale sought in vain for a system enabling a sailor to navigate waters by night in complete safety. He realised there was an opportunity to transfer the technology between the automotive sector and that of boating.

In 2015, he formed an entourage of specialists in the development of software and image processing to develop his EyeSea project, and later Biancale approached Gaëtan Gouerou, the then representative of the IMOCA class and Director of Mer & Projets.

Gouerou opened the door to the world of offshore racing.

In early 2018, the teams of the three Vendée Globe winners, Vincent Riou, François Gabart and Armel Le Cléac’h, agreed to lend their support and their expertise in the drafting of the system’s initial specifications. In May 2018, Biancale and Gouerou created BSB Marine based in Port La Forêt in north-west Brittany.

Since 2017, around fifteen international engineers have been working on the development of Oscar, based on computer vision, a branch of artificial intelligence enabling computers to ‘see’ in a similar way to human beings. In this way, Oscar processes and analyses video feed in elapsed time using the algorithms developed for this maritime artificial vision and alerts the crew at a possible collision risk. Oscar’s artificial intelligence is based on deep learning, which relies on a network of artificial neurons inspired by the human brain. In this way, the more the Oscar database is enriched by information stemming from users’ on-the water experience, the better the system will perform.

Whales, drifting buoys, blocks of wood, waste of all kinds and containers that have fallen off vessels cause all sorts of challenges for sailors.

It’s extremely difficult to gauge the scale of this marine pollution or draw up an annual assessment of the containers lost overboard in the sea, says BSB Marine.

Oscar is said to observe the ocean with two thermal cameras and detects anything that is not water. It learns to identify objects by analysing and processing data collected by users. As its database is enhanced with the acquisition of images of rarer objects, Oscar will eventually be able to recognise even more.

Comments are closed.