An EU-backed project aims to deploy catch scanners using AI on fishing boats to identify fish species, size, and weight. The aim is to help fishers comply with strict regulations and protect stocks.
Category
🗞
NewsTranscript
00:00Bjørtsford is a remote fishing village on Norway's northernmost coast, far beyond the
00:07Arctic Circle.
00:08Though home to just a couple of thousand residents, it's a vital local hub for the fishing industry.
00:14This vessel sets out to seize a brief window between two Arctic storms for a chance of
00:19finding a good catch in these cold, unpredictable waters.
00:24It can be tough. It can be tough, especially in the autumn and winters. The weather is
00:29very unpredictable, very cold. Of course, of course, it can be very bumpy. We work when
00:35it's fish to catch, so it doesn't matter what time of the day it is. Day or night, it's
00:40all the same to us.
00:46This fishing vessel uses a large net to catch massive amounts of fish at once. A good day
00:52could bring in 30 tons of catch. Cod makes the most money, but the nets pull up a mix
00:57of fish species. Unwanted fish can't just be thrown back into the sea. Each of the species
01:04needs to be weighed and logged separately. Inspections can happen any time, and any mistakes
01:09in catch reporting could have serious consequences, including big fines and reduced quota.
01:15The fishing industry in Norway is strictly regulated, so it's very important for us to
01:22have the exact number of what we catch so we can report it to the government. If we
01:27make a mistake, in the worst case scenario, they will take the whole catch away from us.
01:31So that means that all the work we've done catching the fishes is wasted.
01:36But how do you weigh tons of different fish quickly and accurately? Usually, fishers estimate
01:43the total weight by counting containers filled with the fish. But this vessel has a new device
01:48designed to make catch counting easier and more precise. Still in development, the catch
01:53scanner uses AI to identify fish species' size and weight as they move along the conveyor
01:59belt. The aim is to make the process as automatic as possible.
02:04New digital tools on fishing vessels can do much more than just count the catches. Europe
02:10is stepping up its fight against illegal fishing, both at home and around the world. In the
02:16next few years, this will lead to major technological innovations in fishery monitoring, control
02:22and surveillance. Under-reporting of catches can lead to overfishing, harming fish stocks
02:28and ecosystems. The catch scanner is part of Every Fish, a European project developing
02:33smart catch recording tools. It's led by Rachel Tiller, Chief Scientist at Sintef Ocean in Trondheim.
02:41We need to know what's going on out there so that we can solve all of these different
02:46crises. So the climate crisis, biodiversity crisis, we need to have more knowledge about
02:52the ocean. We're looking at a number of different developments in camera technology and machine
02:57vision, artificial intelligence, trying to come up with solutions to put on fishing vessels,
03:02sensors that can help us to automatically record all the fish that come out of the sea.
03:10There are many engineering challenges ahead. For catch scanners to be truly useful, they
03:14must be highly reliable and accurate. Fishers, controllers and scientists need to trust the
03:19data produced by AI on board. To meet this goal, Every Fish researchers have developed
03:28open source AI methods to identify fish species and estimate weights. The engineers work closely
03:34with fishers to ensure their solutions meet real world needs and perform well on rocking
03:39boats in cold, salty seas. It's really important to get the feedback from the industry, from
03:46the vessels, to be able to shape what we are working with here at the lab. If we don't
03:50have that kind of feedback, then we might just go in the wrong direction. To count catches
03:56on smaller boats, researchers are developing computer vision systems that can identify
04:01and measure individual fish in a pile. This could allow artisan and hobby fishers to scan
04:07their catches using CCTV cameras or even smart phones. The same technology could even guide
04:12robotic arms to sort out and handle the catch, taking over some of the hardest manual tasks.
04:21There's a lot of hard labour in the fishing industry in general, so it's hard on the shoulders,
04:24hard on the back, you have to stay leaned over a table, you have to work with the fish.
04:29What you can do is you can perhaps automate some of these processes with robotic arms,
04:34and a clue to doing so is to have good vision systems that are able to parse and understand
04:38the scenes that they're looking at. Onboard surveillance cameras are often used to combat
04:44illegal fishing and other violations. In places like the Seychelles, monitoring officers regularly
04:50review onboard footage to ensure fishers follow the rules. In Europe, video surveillance will
04:55have to comply with strict privacy and data protection laws.
05:02Many fishers are already really sceptical of the system of having some kind of camera
05:07onboard their vessel, and it's absolutely understandable. I would be sceptical as well
05:11if my boss wanted to install a camera in my office. So we are developing systems that
05:17will automatically blur out identifiable elements of humans, so we can comply with GDPR regulations
05:25and also with a sense of personal space. The EU will require surveillance cameras on
05:31high-risk vessels, as well as satellite tracking systems on all fishing boats. These tools
05:36help European Fisheries Control Agency officers in Vigo and Spain monitor fishing and coordinate
05:41inspections. The signal is going to satellite, later down to our systems, and what we have
05:49we can see on the screen. Here we have our vessels, here we have fishing vessels, so
05:54we can count time, how much we needed to get in position. With more fishing vessels getting
06:02equipped with trackers, control centres will have much more data to process. Computer algorithms
06:07can help sift through it all and flag anything suspicious. We have also some automatic tools
06:13that can perform some analysis, for example related with the closed area or the fisheries
06:18restricted areas we have, for example, in the Mediterranean Sea. One of these areas
06:23is the very well-known the Jacuba, Pomopitaria in the Adriatic Sea, where we have some algorithms
06:28defined in order to raise some alerts or some warnings in case of a vessel accessing this
06:35area with certain speed, which could be associated to a potential fishing activity. While digital
06:42tools like cameras and AI are valuable additions to fishery monitoring, experts caution they
06:48have limitations and can sometimes fail. The EU's push for stricter oversight combines
06:53traditional inspections with these new technologies. The surge of digital data is meant to make
06:58fishing more sustainable and fair. I always call it a tsunami of data that will come in.
07:05We will have to look at how we work with that data, which technologies we can use to translate
07:11this data into usable and actionable outputs. We can for that use artificial intelligence,
07:20algorithms, automatic behaviour monitoring tools. All this is very nice, but at the end
07:26of the day, despite all this technology, you will still need the professional input from
07:31the fishery inspector. Digital technology can give fishers handy new tools so they can
07:38spend more time fishing and less time filling forms. It also helps scientists find new ways
07:44to protect the health of our oceans, while making it easier for fishery controllers to
07:48ensure there's plenty of fish in the sea for years to come.