Google released a new AI tool this week, designed to identify animal species to help with wildlife monitoring.
On Monday, the tech giant announced the release of SpeciesNet, an open source model for wildlife biologists. SpeciesNet consists of a model for identifying objects in footage from cameras that monitor wildlife and a second model for classifying those objects into animal species.
Since 2019, wildlife biologists have had access to SpeciesNet though a Google Cloud-based tool called Wildlife Insights. On Monday, SpeciesNet was released to the public as an open source model.
Scientists use motion activated cameras to study wildlife in their habitats. But processing the camera footage is time-consuming because it involves sifting through massive amounts of images. “AI can accelerate that processing, helping conservation practitioners spend more time on conservation, and less time reviewing images,” read the SpeciesNet repository hosted on GitHub.
Google says SpeciesNet was trained on a dataset of over 65 million images including camera trap images from Wildlife Insights users and publicly available datasets. SpeciesNet combines data gathered from its underlying models to make a prediction about each animal it identifies and labels the accuracy percentage.
Credit: Google / University of Minnesota
According to Google, SpeciesNet can “classify images into one of more than 2000 labels, covering diverse animal species, higher-level taxa (like ‘mammalia’ or ‘felidae’), and non-animal classes (‘blank’, ‘vehicle’).”
SpeciesNet is available as an open source model on GitHub.
