News & Views Products Technology
Innovasea unveils tagless fish detection technology

A combination of artificial intelligence and optical camera imaging can count your fish without the stress of handling and tagging.

Aquaculture tech company, Innovasea, is testing a new tagless fish detection technology that can detect, count and classify fish in real time. Early trials indicate that it could be up to 90 per cent accurate in counting and identifying wild fish.

This new project was launched in May through Canada’s Ocean Supercluster, an Ocean Aware 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 leads Ocean Aware, which includes more than a dozen private and public sector partners and supporters.

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 field tested the system in May around the White Rock Dam on Nova Scotia’s Gaspereau River.

“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.”

Innovasea says the company is working to commercialize the new tagless detection technology, which will ultimately work in conjunction with its Fathom software platform.