In Australia, our collaborators at the Wildlife Observatory of Australia (WildObs) have taken the open source SpeciesNet model and trained it to identify species that are not part of the original model, but are locally important. Australia is home to many species found nowhere else in the world, and those species are important for monitoring and conservation. A version of SpeciesNet trained on local wildlife allows teams to look for endemic, threatened or endangered species specific to their area to conserve wild populations.
SpeciesNet can identify species from multiple angles, in different types of light, and when only part of the animal is visible. But sometimes the animals get curious and look directly at the camera, producing a real picture.
The projects above represent just a sample of the groups we have worked with to help use SpeciesNet to interpret camera trap images. Thank you to all our partners who are using this tool on the ground to better understand and protect the wildlife that also call our planet home. To learn more about the history of SpeciesNet, its model training and performance, read our post on the Google Research Blog.
