Spyfish Aotearoa

A citizen science and machine learning approach to identify fish in baited underwater videos.

School of Blue maomao Poor Knights Islands Marine Reserve

School of Blue maomao in Poor Knights Islands Marine Reserve.
Photo by the New Zealand Department of Conservation

A pair of blue cod, an endemic fish of New Zealand

A biodiversity hotspot

Over half of the 17,000 marine species in New Zealand can not be found anywhere else in the world.
School of Blue maomao Poor Knights Islands Marine Reserve

How many?

Counting how many fish are in the ocean and how different threats like fishing, pollution and climate change influence marine ecosystems is a great challenge.

Moki fish photographed as part of a baited underwater video survey

Baited underwater video

A camera pointing to a bait is an ideal non-invasive method to monitor fish populations.

Biologists use this method to know more about the abundance of carnivorous and scavenger fishes.

Underwater photo of snappers facing forward

Hours and hours of footage

Baited underwater videos provide crucial information on the populations of fish species. However, the manual classification of the footage is time consuming.

Wildlife.ai is developing a citizen science and machine learning approach to classify target fish species from underwater footage recorded around Aotearoa/New Zealand.

Spyfish Aotearoa in Action – Making Life Easier For Department of Conservation Rangers

Recently we went out on the boat with Te Papa Atawhai - the Department of Conservation (DOC) to see Spyfish Aotearoa in action and hear more about how it is helping to streamline their processes, and make life easier for DOC rangers.

How Spyfish Aotearoa Is Automating Marine Protected Area Monitoring

Over the past 3 years, Wildlife.ai and Te Papa Atawhai - the Department of Conservation have built a range of tools to efficiently monitor fish populations in Marine Protected Areas in Aotearoa New Zealand. We have created a pipeline to clean and standardise existing data, built apps for uploading new data videos and field information, trained an AI model to recognise snapper and blue cod from baited underwater footage and built a dashboard to present the results.

Eran Paz
Eran PazData ranger
Hiromi Beran
Hiromi BeranCommunity ranger
Ohad Taylor
Ohad TaylorData ranger
Adi Gabay
Adi GabayData ranger
Ben Knight
Ben KnightCommunity Ranger
Monique Ladds
Monique LaddsEcology ranger
Victor Anton
Victor AntonProject ranger
Nitzan Barzilay
Nitzan BarzilayData ranger
Itamar Eraz
Itamar ErazData ranger
Harry Allard
Harry AllardEcology ranger
Matan Atsmony
Matan AtsmonyData ranger
Go to Top