Skip to main content

Classify your own images and movies

The below tutorials will guide your through the notebooks that allow you to use Zoouniverse for annotating movies and images.

Upload clips and frames to Zooniverse

If you want to analyse footage and images, use the below link to run Jupyter notebook "Upload_subjects_to_Zooniverse" and transfer your video clips from Cloudina to Zooniverse. On the right hand side you can find a quick guide.

https://github.com/ocean-data-factory-sweden/kso

Process classifications

If you want to pull and process classifications from Zooniverse, use the below link to run Jupyter notebook "Process_classifications", pull up-to-date classifications from Zooniverse and format these for model training. On the right hand side you can find a quick guide.

https://github.com/ocean-data-factory-sweden/kso

Classify other people's images and movies

Interested to explore underwater footage, learn more about marine creatures and help our scientists to train  machines to detect marine species and habitats? If you haven't done it yet, start creating an account at Zooniverse and then choose one of the below annotation projects. Lets go :).

GobyTrack

We need your help to monitor the spread of an invasive fish along the Swedish coastline. In order to achieve this goal we need you to identify fish and crab species in our movies. One of these species is especially interesting – the invasive round goby (Neogobius melanostomus), a small, bottom dwelling fish that causes ecological havoc in Swedish waters. Your identifications will help us to train machine-learning algorithms which will then automatically search the water for this fish in the future. Your data will directly contribute to marine ecological research and ecosystem management in Sweden! How does that sound, interesting? Well, then let's get started, click here  to get to the Zooniverse project. The "Tutorial" will guide you through the identification process.

Long-term changes in Koster National Park

The Kosterhavets National Park is Sweden's first marine national park with a size of 389 square km. The area contains a Sweden's most diverse marine fauna and many of the bottom dwelling species are otherwise only found in deep Atlantic waters. Large sponges, starfish and cold-water corals are some of them. For the last 30 years, the scientists at the Tjärnö Marine Laboratory have used Remotely Operated Vehicles (ROVs) to monitor the seafloor in the National Park. Here we make footage available for classification in order to train machine-learning models to anlyse the long-term changes in the park.

Spyfish Aotearoa

We also have cameras deployed in New Zealand! Here you can explore the exotic underwater world of  Aotearoa, discover, count and identify unique fish species from marine reserves.