AI-based technology developed as part of Canada’s Ocean Supercluster
Innovasea, a global leader in technologically advanced aquatic solutions for aquaculture and fish tracking, announced that it has begun testing a new tagless fish detection technology that can detect, count and classify fish in real time using a combination of imaging sonar, optical cameras and artificial intelligence.
The promising new technology – developed in conjunction with DeepSense and Nova Scotia Power as part of the Innovasea-led Ocean Aware project – has been shown in early trials to be 90 percent accurate in properly counting and identifying wild fish.
“This novel technology shows incredible potential to detect wild fish that haven’t been tagged by humans and will provide breakthrough capability for hydroelectric dam operators to gain automated, real-time insight into the quantity and type of fish moving near their facilities,” said Mark Jollymore, president of Innovasea. “This new technology could also prove groundbreaking for scientists, researchers and resource managers by helping them vastly expand their knowledge in the years ahead.”
The automated fish detection and classification technology was first tested last year using video of fish swimming around the Wells Dam in Washington’s Columbia River along with proprietary data sets from Emera and high resolution DIDSON imaging sonar captured from the Ocqueoc River in Michigan.
Innovasea and DeepSense will field test the system around the White Rock Dam on Nova Scotia’s Gaspereau River later this month.
“This project is a great example of bringing together different types of data to train an AI model that will automate a resource-heavy, skilled task, thus creating a significantly efficient operation,” said Jennifer LaPlante, executive director of DeepSense. “Partnering with DeepSense enabled all project partners the ability to take risks, access leading AI and machine learning researchers, and recruit valuable AI talent.”
The tagless detection technology was developed to help Nova Scotia Power monitor fish passage around its hydroelectric dams in Nova Scotia. Hydroelectric facilities often use underwater cameras to monitor fish activity around their infrastructure, but employees have to watch recordings of the footage and manually count fish on the screen and attempt to identify the species they see.
“We take our commitment to the environment very seriously,” said Terry Toner, Nova Scotia Power’s senior director of strategic environmental projects. “If successful, this technology could further strengthen our protection of fish and the environment while improving the efficiency of our hydro operations.”
A key part of Canada’s Ocean Supercluster, the Ocean Aware project is an initiative designed to develop world-class solutions for monitoring fish health, fish movement and the environment to support both profitable and sustainable practices in the ocean. Innovasea is leading Ocean Aware, which includes more than a dozen private and public sector partners and supporters. “Ocean Aware and the exciting advances made in the project are an example of the kind of cross-sectoral collaboration we are creating through Canada’s Ocean Supercluster,” said Kendra MacDonald, CEO of Canada’s Ocean Supercluster. “The ability to better understand our ocean environment, including fish movement and health, helps inform decision-making and the sustainable growth of our ocean – a space where Canada can lead with its technology.”
Innovasea is working to commercialize the new tagless detection technology, which will ultimately work in conjunction with its Fathom software platform.
