Google releases AI model for wildlife identification  

Researchers can now integrate SpeciesNet into remote camera toolkit

Google has released SpeciesNet, its artificial intelligence model for wildlife identification, to the public. Google first launched its model in 2019 on its cloud-based tool, Wildlife Insights, which has helped scientists around the world identify species in trail camera images. While remote cameras are useful tools for monitoring hard-to-study species in remote areas, they capture large amounts of data that take a lot of time for scientists to sift through. Now that the tool is open-source and available to the public, developers, academics and other researchers can use SpeciesNet in their own wildlife monitoring and management projects. Google said that SpeciesNet was trained on over 65 million publicly available images and can classify animals in up to 2,000 categories at higher taxa right down to the species level.

Read more at TechCrunch.

Header Image: Researchers use trail cameras to detect a wide variety of species, from small ground-dwelling birds to large carnivores. Credit: P Jeganathan