Maritime news: new algorithms track ships in ports

Identifying a vessel in a computer image may seem simple, but PhD researcher Amir Ghahremani now knows that nothing is what it seems. “Vessels come in different shapes and move at different speeds. And when they’re away, all you see on screen are a few vague pixels. Try to recognize a boat in there! In addition, water and weather conditions often make vessel identification even more difficult. Bright sun causes glare, and fog or heavy rain also reduces image quality. In short, a very dynamic environment.

Boat Giethoorn

As part of the international Applying Plug & Play Surveillance (APPS) project, Ghahremani has collaborated with various universities, institutes and industrial partners around the world on innovative algorithms to improve automated maritime surveillance systems. These systems are not only used to ensure the security of port areas, but also of maritime territories and busy waterways and canals.

Researchers set out to develop a robust system suitable for widely varying conditions. However, they had no visual footage to test their algorithms, so Ghahremani first spent a month filming and collecting photos. This included photos of ships in the ports of Amsterdam and Rotterdam, boats in Turkish ports and his favourite: the village of Giethoorn, famous for its canals and boats.

But you won’t find any container ships in Giethoorn. Instead, the canals are crowded with pleasure boats for tourists, especially in high season. Ghahremani eventually ended up in a traditional punt boat. And not without results, he admits with a smile, because it taught the Iranian-born researcher with a predilection for mountains to appreciate the flat, water-rich Dutch countryside. In fact, he even became a Dutch citizen recently.

Sharon D. Cole