N+1 fish, N+2 fish Hosted By DrivenData

5 weeks left
$50,000.00

About the project


New England’s groundfish fishery is part of the region’s $2 billion seafood industry that supports more than 100,000 jobs. Every day, boats small and large leave from docks along the New England coast in search of fish. The modern fishing boat is a combination of high and low tech, with nets that could have come from 100 years ago alongside satellite tracking systems and digital depth finders. Today’s fishermen work hard to catch enough to make a living, while leaving enough fish for the next season. Today’s seafood consumers demand more information about the sustainability of what’s on their plate. With better data, we can meet the goals of seafood producers, managers, scientists, and eaters.

The United States is considered a global leader in fisheries management because of its strong commitments to keeping fish populations at healthy levels. This puts additional requirements on fishing boats to demonstrate they’re meeting those standards. Electronic monitoring systems, like video cameras, could offer an affordable way for fishermen to show their work and keep consumers and fisheries managers confident in the sustainability of their seafood. People are already using machine learning to track fishing boats on the high seas, and to count tuna in the Pacific Ocean. We want to bring that automation to the hundreds of boats fishing along the New England’s coast.

This competition is the first to use actual fishing video to develop tools that can classify multiple parameters, such as size and species. With more and more fisheries adopting video camera monitoring, the results of this competition will have real-world impacts for ocean conservation and fishing communities.

A handful of fishing innovators worked with The Nature Conservancy and the Gulf of Maine Research Institute to install video monitoring systems on their boats. These cameras have provided the training images for this contest. On why he's part of this pilot program, Mike Russo, captain of the f/v Gulf Venture, of Provincetown, Mass says:

"Cameras on boats will make a big difference for two reasons. One, you won’t have an inexperienced person onboard, which is a liability and a safety risk, and two, pictures don’t lie: Video footage will validate fishermen’s observations, which up until now have been categorized as anecdotal. Now, the proof will be there.”

alt-text

Cundy’s Harbor fisherman Bryan Bichrest in the wheelhouse viewing the monitor showing video feeds from all four of the cameras onboard his boat. Image © Heather Perry for The Nature Conservancy

Project Team

This project is a first-time collaboration of a team of machine learning and fisheries experts. Kate Wing, the project manager, founded the databranch to tackle high-impact conservation data challenges, and has 20 years of ocean experience. To develop the project scope, she worked with The Nature Conservancy's Chris McGuire, the Director of Marine Programs at TNC’s Massachusetts Chapter who also leads their New England electronic monitoring program. Matching their saltwater specialities are engineer Ben Woodward, co-founder of CVision image consulting and a Signals Processing Engineer at Draper, and computer scientist Joseph Paul Cohen, Postdoctoral Fellow at Montreal Institute for Learning Algorithms. Together, the team worked to build a competition that would benefit fisheries and maybe get a few more people hooked on fish.